Article

Analysis of the perceived value of online tourism reviews: Influence of readability and reviewer characteristics

Authors:
To read the full-text of this research, you can request a copy directly from the authors.

No full-text available

Request Full-text Paper PDF

To read the full-text of this research,
you can request a copy directly from the authors.

... Travelers have to read a large number of reviews to obtain desired information about the accommodation to make a purchase decision [26]. Due to the high volume of online reviews possessed by todays' hotels, review readers are facing difficulties as they have to manually process all the information [5,14,15,26]. It significantly increases the search cost to find hotel reviews that help to meet their goals [15]. ...
... [13] conducted a meta-analysis and found the review rating didn't significantly influence the helpfulness of the review. The most important aspect of a review is the review content [18,5]. Compared to the overall review score of a review, the content of the review provides more information about hotel accommodation experience and traveler opinions about the stay [27]. ...
... The Flesch Reading Ease scale ranks texts from 1 to 100, with 100 being the greatest readability score [36]. [5,9,17] found that the readability of the review positively affects review helpfulness. The subjectivity of a text refers to the tendency to interpret data or make judgments in the light of personal beliefs, experiences, and feelings [35]. ...
Conference Paper
Full-text available
Tourism has grown in popularity across the world over the years and it was one of the first industries to digitally transform business processes on a worldwide scale. People eventually started to book their itineraries online and share their experiences through online booking platforms. The enormous number of internet hotel reviews has created an issue of information overload. Review readers have to sacrifice their time and mental effort to find helpful reviews from the rest. Therefore, the identification of the most helpful reviews has emerged as a critical research topic. The purpose of this study is to propose a classification model to identify such helpful reviews from the rest, which would reduce the search cost and mental effort of travelers who are looking forward to making online reservations. Online reviews were collected from the Tripadvisor website. Review content quality, reviewer characteristics, review sentiment, and the recency of the review have been considered to build the classification model. Several prediction models were developed based on classification techniques for review helpfulness. After classifying reviews the model with the best prediction performance was used for further experiments. Results ensure that reviewer characteristics have the highest impact and subjectivity score has the lowest impact on the helpfulness of the review.
... According to Schuckert et al. (2015), almost 71% of independent travel-related bookings are made online, while 36% of all package tours are also booked online. Moreover, 65% of travelers looking for leisure activities or vacations look for information online before deciding to travel, and 69% of their plans are determined by online travel reviews (Fang et al., 2016). ...
... According to Fang et al. (2016), reviews with a clear and explicit writing style are perceived as more useful. Academics observed perceived usefulness as a cognition process dependent on accepting or not the existent technology (Mou et al., 2017), reflecting in consumer's behaviors (intention) regarding purchasing from an online source (Ashraf et al., 2016). ...
... In the global sentiment analysis, it is clear that the reviewers' sentiments are very positive. That positive sentimentalism demonstrated in reviews can be considered useful (Fang et al., 2016), influencing the customer's decision-making (Ashraf et al., 2016). The reviews can convert readers into customers of a destination, as comments with higher polarity can influence potential tourists of a destination (Alaei et al., 2019). ...
Article
This study explores how tourists perceive two island destinations (Madeira and Bermuda) through reviews on social network platforms. An Artificial intelligence data mining methodology is used (text mining) to address the research problem. Authors collected TripAdvisor reviews, 1148 from Madeira and 635 from Bermuda (total pool of 1783 reviews). A database with three coding was generated, based on literature: Tourism Experience Model (TEM), Membership Level of reviewers (ML) and Categories. Data was analyzed through Meaning Cloud software. Results point out an overall customer satisfaction regarding both islands, but slightly superior for Madeira’s island. This research also discusses reviewers ranking level, the type of language in use, and the generation of negative content. It is possible to conclude that reviews can persuade others, namely their booking intention.
... Against this background, the e-commerce has also developed rapidly. Many e-commerce platforms increasingly support consumers to make online reviews on the products they have purchased [1][2][3]. Decision analysis based on online reviews has generated considerable recent research interest. e existing researches have shown that online reviews have important reference value for product selection, especially when consumers are buying products with higher prices [4,5]. ...
... erefore, how to make full use of online reviews needs further study. (2) In this paper, only the objective weight of each attribute is considered in the ranking process of alternatives. However, the subjective weight provided by consumers is also crucial in the ranking process. ...
Article
Full-text available
With the rapid development of information technology and market economy, global e-commerce platform develops rapidly. Recently, online reviews are widely available on e-commerce platforms to express customers’ experience of products. When ranking alternative products based on online reviews, how to make full use of the information in online reviews to represent the sentiment analysis results of online reviews is an important prerequisite for decision analysis. To this end, we propose a method for measuring the time utility and support utility of online reviews. Then a method for representing the sentiment analysis results of online reviews in the form of linguistic distribution is proposed. In addition, in view of the attributes and their weights being unknown, we propose a method for extracting product attributes from online reviews by using the Term Frequency-Inverse Document Frequency (TF-IDF) algorithm; and the objective weights of attributes are determined through the Criteria Importance through Intercriteria Correlation (CRITIC) method. Additionally, in order to highlight the differences between the alternatives, the roulette wheel selection algorithm is first used to randomly select product attributes. Then the alternative products can be ranked by the extended Multi-Attributive Border Approximation area Comparison (MABAC) method with mixed information. Finally, we illustrate the applicability of the proposed method through a case study of selecting a 5G mobile phone and simulation experiment.
... The researchers discovered that by mining consumer opinions, a corporation may also watch how customers interact with the service or product and determine how their attitude toward it has evolved. includes the branch of computational linguistics known as opinion mining, which is concerned with the examination of online media for the extraction, appraisal, and comprehension of opinions expressed in that type of media opinions [9], approaches, methodically explores for people's views [10], works to uncover problems, methodically studies and how people react to topics or personalities, and then records what is learned [11]. Because we behave based on what we believe to be right and wrong judgments about others, our behaviours are significant. ...
... The investigation shows that the Naive Bayes classifier outperforms other classification algorithms by using an effective strategy. SAAS online feedback mood was predicted using controlled machine learning approaches by Fang et al. [9]. The author conducted research into how customers feel about cloud storage services. ...
Article
The advent of social networking and the internet has resulted in a huge shift in how consumers express their loyalty and where firms acquire a reputation. Customers and businesses frequently leave comments, and entrepreneurs do the same. These write-ups may be useful to those with the ability to analyse them. However, analysing textual content without the use of computers and the associated tools is time-consuming and difficult. The goal of Sentiment Analysis (SA) is to discover client feedback, points of view, or complaints that describe the product in a more negative or optimistic light. You can expect this to be a result based on this data if you merely read and assess feedback or examine ratings. There was a time when only the use of standard techniques, such as linear regression and Support Vector Machines (SVM), was effective for the task of automatically discovering knowledge from written explanations, but the older approaches have now been mostly replaced by deep neural networks, and deep learning has gotten the job done. Convolution and compressing RNNs are useful for tasks like machine translation, caption creation, and language modelling, however they suffer from gradient disappearance or explosion issues with large words. This research uses a deep learning RNN for movie review sentiment prediction that is quite comparable to Long Short-Term Memory networks. A LSTM model was well suited for modelling long sequential data. Generally, sentence vectorization approaches are used to overcome the inconsistency of sentence form. We made an attempt to look into the effect of hyper parameters like dropout of layers, activation functions and we also tested the model with different neural network settings and showed results that have been presented in the various ways to take the data into account. IMDB is the official movie database which serves as the basis for all of the experimental studies in the proposed model.
... Though this work considers the quality of reviews, it overlooks the positional influence of each customer. In Fang et al. (2016), the authors focus on the length of reviews and its effect on product sales is discussed. They assume that customers always prefer quick sources of information regarding the quality of items. ...
... 4405 books. Fang et al. (2016) Sentiment on review text and how length of reviews relates to product sales. 19,674 online reviews of a tourism destination (i.e., New Orleans) from TripAdvisor. ...
Article
E-commerce companies want to predict their future product sales from the current customers’ feedback to frame a better business strategy. However, the conventional way of analyzing rating activities or quality and sentiment of reviews, volume of sales, or product prices is not enough for establishing a strong regression between these parameters and future product sales. Most of the existing works ignore the heterogeneous positional and influential effects of individual customer reviews and ratings. For the realization of these effects, we use review network i.e., a bipartite network between customers and products based on the customers’ review activities. In this paper, we present a concept named Network Promoter Score (NePS) based on the reliability, positional influence of each customer in the network. In-depth experiments on online review datasets show that NePS emerges as a strong indicator of product sales and can be remarkably futuristic compared to the existing parameters. Furthermore, we propose a predictive modeling technique to estimate the product sales of a company based on NePS.
... The existing literature on this topic reports mixed and contradictory findings. For instance, Kwok and Xie (2016) found that review length has no effect on the perceived helpfulness of reviews; on the contrary, Fang, Ye, Kucukusta, and Law (2016) found this effect to be positive. Likewise, Liu and Park (2015) showed that review length has a positive impact on the review's perceived usefulness, but Filieri, Hofacker, and Alguezaui (2018) found that it has no positive effect on perceived information diagnosticity. ...
... The study also assesses whether these effects vary on the basis of the structure classification (i.e., 3-, or 5-star hotels), as different hotel categories may lead to different consumer expectations. As hotel star class (HSC) is a wellestablished international scheme, thus reflecting the varying quality and services owned by hotels (Fang et al., 2016;Hu and Chen, 2016), we hypothesize that unfavorable reviews are significantly lengthier than favorable ones only for 5star hotels (H2a). ...
... In considering the multiple review types and related key issues, however, helpfulness is quite a nuanced term, as quantitative measures of reviews are equally useful, whereas others might consider qualitative characteristics as more helpful [15]. Fang et al. [17] indicated that text readability significantly influences perceived RH. Mauro et al. [18] revealed that review wordiness is a meaningful predictor of RH. e study of Malik and Hussain [19] indicated that discrete emotions are the most dominant emotions with greater influence on perceived RH. ...
... It has also been assumed that the disease type as a feature moderates the association between readability and RH. In the services sector, a more readable review can be assessed more simply than a review with spelling mistakes and ambiguous words [17,50]. Similarly, patients who suffer from serious diseases expect that information embedded in a review should be more readable than those who suffer from mild diseases. ...
Article
Full-text available
(1) Background. Patients are increasingly using physician online reviews (PORs) to learn about the quality of care. Patients benefit from the use of PORs and physicians need to be aware of how this evaluation affects their treatment decisions. The current work aims to investigate the influence of critical quantitative and qualitative factors on physician review helpfulness (RH). (2) Methods. The data including 45,300 PORs across multiple disease types were scraped from Healthgrades.com. Grounded on the signaling theory, machine learning-based mixed methods approaches (i.e., text mining and econometric analyses) were performed to test study hypotheses and address the research questions. Machine learning algorithms were used to classify the data set with review- and service-related features through a confusion matrix. (3) Results. Regarding review-related signals, RH is primarily influenced by review readability, wordiness, and specific emotions (positive and negative). With regard to service-related signals, the results imply that service quality and popularity are critical to RH. Moreover, review wordiness, service quality, and popularity are better predictors for perceived RH for serious diseases than they are for mild diseases. (4) Conclusions. The findings of the empirical investigation suggest that platform designers should design a recommendation system that reduces search time and cognitive processing costs in order to assist patients in making their treatment decisions. This study also discloses the point that reviews and service-related signals influence physician RH. Using the machine learning-based sentic computing framework, the findings advance our understanding of the important role of discrete emotions in determining perceived RH. Moreover, the research also contributes by comparing the effects of different signals on perceived RH across different disease types.
... It is essential that destination managers and marketers understand in-depth components of tourist experiences at these tourist attractions to manage destination competitiveness and tourist satisfaction. So far, only a few studies such as the works by Taecharungroj and Mathayomchan (2019) in Thailand, Fang et al. (2016) and, Kirilenko et al. (2019) in the U.S., and Simeon et al. (2017) in Italy have examined online reviews of tourist attractions using machine learning techniques to assess tourist experiences. These studies mainly use the TripAdvisor platform as the data source. ...
... Therefore, online reviews offer to reduce the tourists' travel risk perceptions and enable them to maximize their holiday experiences and enjoyment at the destination. Due to these benefits, more and more tourists rely on online reviews to make travel and holiday purchase decisions (Buhalis & Law, 2008;Fang et al., 2016). As online reviews continue to play a growing significant role in travel decision-making, there is a continued surge in destination and tourist experience research that utilizes online reviews as data for the studies. ...
Article
Full-text available
This study attempts to analyze the dimensions of the night market visit experience of international tourists. Based on a two-step analysis of 13,833 Google review comments collected for the nine most popular night markets in Phuket, two key dimensions—market experience and food experience—were identified. Overall, the tourists were highly satisfied with their night market experiences. The results of machine learning analysis using the KNIME analytics platform indicate that the market experience dimension was more positive in valence and higher in salience than the food experience dimension. In addition, food was found to be the most important component in both market experience and food experience dimensions. The content analysis results of both positive and negative reviews show factors that determine tourist satisfaction, including a variety of food and stores, affordable prices, and a pleasurable atmosphere. On the other hand, factors being of serious concern to tourists were also identified and are discussed, most of which relate to the food experience dimension, including food hygiene, staff attitude, and overcharging.
... This fact is explained by the adaptation-level theory [59] that highlights that the service and prior experience influence expectations. Tourist feedback is considered more realistic when conducted by those with more experiences [60] since tourists can compare the experience with past experiences. Thus, the following hypothesis is proposed: ...
... Previous experiences affect expectations, influencing satisfaction [57]. Tourists have a more realistic experience compared to previous ones [60]. ...
Article
Full-text available
Tourism has been fundamental for countries’ economic development, and Africa is the destination with the biggest tourism growth potential. Using 1414 travelers’ online reviews collected from TripAdvisor, the present work aims to understand which variables predict the satisfaction of Cape Verde’s hotel clients. Satisfaction was analyzed using sentiment analysis and ANOVA to predict the effect of the gathered variables on clients’ satisfaction. Results indicate that 90% of the clients revealed positive satisfaction and that nationality, date of stay, and previous traveler experiences affect satisfaction. Contrarily to our predictions, there is no statistically significant evidence that gender influences satisfaction. The findings of this study will help hotel marketing managers to align their strategies accordingly and meet their clients’ expectations.
... Previous research has claimed that what moves people to travel and, simultaneously, what lures them to visit certain destinations is simply motivation [45,46]. In the past, several studies were conducted in order to pinpoint the push and pull factors that contribute to forge tourists' motivations, in addition to elucidating how to utilize these factors in the creation of more effective marketing strategies [26,[45][46][47][48][49][50] (see Table 3). [56] Push and pull motivation 2010 Jordan A number of previous studies have also emphasized social media relevance in terms of offered services and products. ...
Article
Full-text available
In recent years, the citizens of Taiwan have exhibited an increasing demand for domestic tourism and travel options. Due to their relatively early development as a domestic tourism destination, the Penghu Islands are well known for their rich natural and cultural resources. The purpose of this study was to examine factors influencing tourists’ visits to Qingwan Cactus Park, including their reasons for visiting and their perceptions of their visits. With principal component analysis serving as the basis for an IPA methodology, and using the visiting destination as a reference point, the results obtained can provide a basic guideline for tourism planning. The visitors’ reactions and demands were re-examined through IPA analysis. The results could be used by national park managers to develop constructive suggestions on implementing sustainable development in Taiwan’s tourism industries. This study presents valuable data on Penghu and provides analyses of residents’ and tourists’ opinions, as well as their reactions. The study’s conclusions can be extrapolated to research on other destinations outside of Taiwan.
... Although more readable content is easier to understand and less aversive than less readable content [41], greater reading difficulty and comprehension can engender more interest, attention, and engagement [42,43]. It can also facilitate deeper cognitive processing that leads to greater learning and long-term retention [44,45]. ...
Article
Full-text available
Linguistic features of a message necessarily shape its persuasive appeal. However, studies have largely examined the effect of linguistic features on persuasion in isolation and do not incorporate properties of language that are often involved in real-world persuasion. As such, little is known about the key verbal dimensions of persuasion or the relative impact of linguistic features on a message’s persuasive appeal in real-world social interactions. We collected large-scale data of online social interactions from a social media website in which users engage in debates in an attempt to change each other’s views on any topic. Messages that successfully changed a user’s views are explicitly marked by the user themselves. We simultaneously examined linguistic features that have been previously linked with message persuasiveness between persuasive and non-persuasive messages. Linguistic features that drive persuasion fell along three central dimensions: structural complexity, negative emotionality, and positive emotionality. Word count, lexical diversity, reading difficulty, analytical language, and self-references emerged as most essential to a message’s persuasive appeal: messages that were longer, more analytic, less anecdotal, more difficult to read, and less lexically varied had significantly greater odds of being persuasive. These results provide a more parsimonious understanding of the social psychological pathways to persuasion as it operates in the real world through verbal behavior. Our results inform theories that address the role of language in persuasion, and provide insight into effective persuasion in digital environments.
... UGC is the content generated by users to express their views on people, events, and things. It can not only fully express user real ideas on people, events, and things, but also express their subjective feelings [15]. UGC has become one of the most important data sources for big data business analysis [16]. ...
Article
Full-text available
Studying recommendation method has long been a fundamental area in personalized marketing science. The rating data sparsity problem is the biggest challenge of recommendations. In addition, existing recommendation methods can only identify user preferences rather than customer needs. To solve these two bottleneck problems, we propose a novel implicit feedback recommendation method using user-generated content (UGC). We identify product feature and customer needs from UGC using Convolutional Neural Network (CNN) model and textual semantic analysis techniques, measure user-product fit degree introducing attention mechanism and antonym mechanism, and predict user rating based on user-product fit degree and user history rating data. Using data from a large-scale review sites, we demonstrate the effectiveness of our proposed method. Our study makes several research contributions. First, we propose a novel recommendation method with strong robustness against sparse rating data. Second, we propose a novel recommendation method based on the customer need-product feature fit. Third, we propose a novel approach to measure the fit degree of customer needs-product feature, which can effectively improve the performance of recommendation method. Our study also indicates the following findings: (1) UGC can be used to predict user ratings with no user rating records. This finding has important implications to solve the sparsity problem of recommendations thoroughly. (2) The customer need-based recommendation method has better performance than existing user preference-based recommendation methods. This finding sheds light on the necessity of mining customer need for recommendation methods. (3) UGC can be used to mine customer need and product features. This finding indicates that UGC also can be used in the other studies requiring information about customer need and product feature. (4) Comparing the opinions of user review should not be solely on the basis of semantic similarity. This finding sheds light on the limitation of existing opinion mining studies. 1. Introduction In the past decade, with the rapid development of online retailing, recommender systems have deeply affected the daily life of people. When people search for a particular product, they will be recommended several products according to their preferences. When they read books or watch movies, the corresponding commodities will be recommended to them. These all show that much of our daily life is invisibly guided by the recommender system. Recommender systems also bring huge benefits to online retailers. For instance, 30% sales of Amazon are increased by the application of recommender system [1]. Researchers find that a minor improvement in the quality of recommender systems can bring millions of dollars in revenue every year to every online retailer [2]. Given the enormous prospects in the promoting product sales, studying the recommendation method to match products and target user has long been a fundamental area in personalized marketing science. So far, recommender system technology still faces great challenges. According to a survey conducted by Tencent, 86% of users have used recommender systems, but more than half of them believe that only a small part of the products recommended can meet their own needs [3]. It reveals that the existing recommender methods fail to satisfy needs of customers, leaving huge room for improvement. Among them, the rating data sparsity problem is the biggest challenge faced by all existing recommendation methods. The existing mainstream recommendation methods include content-based recommendation methods, collaborative filtering methods, hybrid recommendation algorithms, and rule-based recommendation methods [2, 4–6]. They are all overreliant on user rating records. With the decrease of rating records, the accuracy of recommendation methods will drop sharply, which brings the rating data sparsity problem. In recent years, major advances have been made in overcoming the sparsity problem. For example, to improve the performance of matrix factorization recommendation method, which is one of the most popular modern recommendation methods, R. Du et al. [7] add user attribute information, Liu et al. [8] add product content information, Yulong Gu [9] adds contextual information, He et al. [10] and Rong-Ping Shen et al. [11] add user feedback information, and Li and Guo [12] add user local characteristics. These studies have alleviated the sparsity problem to a certain extent, but they are still unable to predict user ratings without user rating record. To completely solve the sparsity problem, implicit feedback recommendation has gradually become one of the most fascinating recommendation research areas. Existing implicit feedback recommendation methods recommend products mainly using user purchase history [13]. For example, some of them utilize user video browsing history or purchase history to recommend videos or products [14]. In fact, both user rating and user purchase history can only be used to identify user preferences, but they do not contain other detailed information about customer need. The reason why users buy products is that the products can satisfy their needs. Therefore, existing recommendation methods can only identify user preferences rather than customer needs, which will inevitably affect their recommendation performance. To solve the problems mentioned above, we propose a novel implicit feedback recommendation method using user-generated content (UGC). UGC is the content generated by users to express their views on people, events, and things. It can not only fully express user real ideas on people, events, and things, but also express their subjective feelings [15]. UGC has become one of the most important data sources for big data business analysis [16]. We propose method predicts user ratings based on customer need identified from UGC and can effectively predict user ratings without any user rating record or user purchase history. To demonstrate the superiority of our proposed method, we compare it with several benchmark methods including Convolutional Matrix Factorization (ConvMF) [17], Neural Graph Collaborative Filtering (NGCF) [18], Deep Factorization-Machine based Neural Network (DeepFM) [19], Probabilistic Matrix Factorization (PMF) [20], and User-based Collaborative Filtering (CF) [21]. The remainder of the paper is organized as follows. In Section 2, we review relevant previous research and discuss the differences between our proposed method and existing methods. In Section 3, we propose a novel personalized implicit feedback recommendation method using user-generated content in detail. To demonstrate the superiority of our proposed method, in Section 4, we evaluate its effectiveness on real data using representative existing methods as benchmarks. Finally, in Section 6, we summarize the findings of this study, discuss them, and conclude with the future work. 2. Literature Review 2.1. Research on Recommendation Algorithm The core technology recommendation system is recommendation algorithm. Existing recommendation algorithms mainly include content-based recommendation algorithms, collaborative filtering recommendation algorithms, hybrid recommendation algorithms, and recommendation algorithms based on association rules. The content-based recommendation algorithm is to analyze the product content to establish the similarity relationship between the products and then recommend similar products with high user ratings [22]. It recommends items based on the product features extracted from product content information. For example, Koren et al. [23] use the information extracted from movie description, such as movie category, actor, and director, to compare the similarity of movies. Deldjoo et al. [24] extract video features from video content using analysis techniques. Shu et al. [5] learn implicit features in product description text using convolutional neural network. Yu et al. [25] extract image features from image content using image analysis technology. Yong Wu et al. [26] extract the label that can describe the product from the text information of the product. In summary, existing content-based recommendation research extracts product features from product content information (such as the description of the product by merchants), and the product content information provided by merchants does not fully reflect the product, which will inevitably affect the matching accuracy of the product and the target user. The collaborative filtering recommendation algorithm analyzes user preferences through user rating records to match products with target users. This kind of recommendation algorithm only needs user rating record data to achieve matching, so it has become the most widely used recommendation algorithm. Collaborative filtering recommendation algorithms can be divided into two categories: memory-based collaborative filtering recommendation and model-based collaborative filtering recommendation. Based on rating records, the memory-based collaborative filtering recommendation algorithm analyzes the similarity of user preferences or the similarity of products through rating records and then recommends high-scoring products purchased by users with similar preferences or high-scoring products similar to those purchased by users [4, 5, 27–30]. This type of recommendation algorithm is very sensitive to rating data. Once the rating data is sparse, its performance will drop sharply, and it is unable to obtain the user's preference for the specific features of the product or to match the recommendation with the target customer. The model-based collaborative filtering recommendation algorithm, which can also be named as matrix factorization (MF) recommendation algorithm, trains the relationship between products and users, users and users (or between products and products), through user history rating data, and can still accurately match products and target customers when the rating data is sparse [23, 31–33]. It is noted that MF recommendations are still based on user rating history records. Without rating records, it cannot work at all. Hybrid recommendation algorithms avoid or make up for the weaknesses of their respective recommendation algorithms by combining content-based recommendation algorithms and collaborative filtering recommendation algorithms. It recommends items based on both the product features extracted from product content information and user history rating records. For example, Toon De Pessemier et al. [6] propose a hybrid algorithm based on content recommendation, collaborative filtering recommendation, and knowledge-based recommendation. Cai Biao et al. [34] propose an improved dual-parameter hybrid recommendation algorithm, which applies particle swarm optimization (PSO) to the parameter optimization of the hybrid recommendation algorithm. Li et al. [35] propose a hybrid recommendation algorithm based on content and user collaborative filtering to solve the problems of data sparsity and cold start. Although hybrid recommendation can solve the problem in collaborative filtering recommendation to a certain extent, especially sparsity and cold start, it still cannot work without user history rating records. In addition, there exists another kind of recommendation methods: implicit feedback recommendation method. They are mainly based on association rules and learn the association rules between products and users based on the user's purchase history [2, 36–38]. Association rules are very widely used pattern recognition algorithms, which are used in shopping analysis and network analysis. Implicit feedback recommendations do not require rating records, but they need user shopping purchase history, which will also bring sparsity problem. 2.2. Researches on Customer Needs Mining Based on User-Generated Content Customer personalized needs belong to the category of the user personalized behavior. Using user-generated content data (UGC) to analyze user behavior has become very hot in recent years, which is widely used in online marketing [39], public opinion analysis [40], and social media operations [41]. UGC can help companies understand customer needs more fully and deeply, so as to (1) improve product design [42]; (2) manage and innovate products [43, 44]; (3) analyze user preferences for product features [45, 46]; and (4) analyze products competitiveness [47]. These studies have fully proved that UGC is an important source of extracting customer needs. However, these studies mainly focus on mining the needs of user groups for product characteristics; they rarely involve the mining of individual needs of customers. To achieve accurate personalized recommendation, it is necessary to further study how to mine individual personalized needs from UGC. There also exist researches using UGC for the performance improvement of recommendation methods. Utilizing the text mining techniques, they propose hybrid recommendation methods that combine user opinion mined from UGC with traditional recommendation methods. These research works are based on both UGC and rating records. For example, using text sentiment classification technique, mine user opinion information from UGC to improve matrix factorization recommendations [48–50], collaborative filtering recommendations [51], hybrid recommendations [52], sequential recommendations [53], and cross-domain recommendations [54]. These researches have demonstrated that UGC can be used to improve the performance of current recommendation methods. However, they still rely on user history rating records or user purchase history. In addition, they only focus on the sentiment analysis of UGC, failing to perform in-depth customer needs mining from UGC. In summary, current recommendation methods are mainly divided into content-based recommendations, collaborative filtering recommendations, hybrid recommendations, and rule-based recommendations (implicit feedback recommendations). These four categories of recommendation methods have their own merits, but they all face the same challenge that when the data is sparse, the performance of the recommendation algorithm will drop sharply. Researchers alleviate the sparsity problem by considering information mined from UGC, although they rely on user rating history records and cannot work at all without these records. On the other hand, existing recommendation methods can only identify user preferences rather than customer needs, which will inevitably affect their recommendation performance. In order to solve the challenges of the abovementioned related research, we propose a novel implicit feedback recommendation method using UGC. 3. A Proposed Personalized Recommendation Method Using User-Generated Content As shown in Figure 1, the proposed method consists of six stages(i)Stage 1. Text preprocessing: We perform text preprocessing such as word segmentation, depunctuation, and stop word removal on the extracted raw UGC.(ii)Stage 2. Identifying informative sentences: We train word embedding with a CBOW model to map words onto a numerical vector space that can be calculated and then train the convolutional neural network model to identify the informative sentences that can present customer needs.(iii)Stage 3. Identifying topic of informative sentences: We extract key words from informative sentences with K-means clustering algorithm to construct a key word vocabulary and mark the topic of each informative sentence based on the constructed key word vocabulary.(iv)Stage 4. Constructing product feature vector and customer needs vector: We calculate the sentence vector of the informative sentences, group all the informative sentences with the same topic and calculate central vector of each sentence group, use text sentiment analysis technology to identify customer need sentences from the informative sentences, and construct product feature vector and customer needs vector.(v)Stage 5. Measuring user-product fit degree: We measure user-product fit degree according to the following three steps: (1) We measure the extent of need the user has for product feature. (2) We measure customer need-product feature fit degree by introducing attention mechanism and antonym mechanism. (3) We measure user-product fit degree.(vi)Stage 6. Predicting user ratings: We predict users’ rating of each product based on user-product fit degree and user history rating data.
... Gretzel and Yoo (2008) report that readers often perceive other customer reviews as more up-to-date, enjoyable and reliable than information provided by service providers. Reviews expressing extreme sentiments are considered valuable by other customers (Fand et al., 2016). Vermeulen and Seegars' (2009) studied the impact of online hotel reviews on tourists in Holland. ...
The purpose of the study is to identify critical value-creating elements of luxury services expressed in ratings and reviews posted on third-party sites and examine cross-cultural differences. To this end, the research analyzed online ratings and reviews of luxury hotels posted on TripAdvisor from customers of four European regions (East, North, South and West). Eight hundred thirty-eight online user-generated ratings and reviews of luxury hotels were analyzed quantitatively using MANOVA and qualitatively using text analysis. The study findings support (a) that product and physical evidence are the most critical experiential elements of luxury hotels' offerings and (b) cultural differences among tourists from various regions of Europe in their hotel ratings and reviews. Specifically, Eastern and Northern Europeans are more generous in their review ratings than western and southern Europeans. Moreover, eastern Europeans value the hotel's physical evidence/environment whereas western Europeans prioritize the core product (room and food) followed by the physical environment/servicescape. Southern Europeans and Northern Europeans value most the personnel, followed by the physical environment and the core product, respectively. Cultural differences provide several implications with regard to luxury services segmentation, social media management, service marketing mix development and hotel promotion. The value of this study originates from studying post-purchase customer behavior in luxury services from a cross-cultural perspective. Moreover, identifying critical aspects of value-creating customer experience in a luxury context adds to the available literature.
... However, online reviews given by other tourists have both positive and negative impacts on choosing hotels [4]. While choosing a hotel, a huge number of reviews may increase the difficulty in the process of choosing the appropriate hotels [5,6]. Then how to select hotels on a tourism Web site based on online reviews would be a question worthy of study. ...
Conference Paper
Nowadays, online review on tourism Web site to select hotels has a great impact on hotel industry. According to existing studies, it is highly likely that the decisions of tourists will be modified after browsing the online reviews given by other tourists on tourism Web site. How to utilize the online reviews on tourism Web site to select hotels and help tourists is a problem to be investigated. Online reviews of one hotel have been given by different previous tourists with respect to different criteria; hence, each tourist can be treated as a decision maker. The problem of selecting hotels based on these online reviews on tourism Web site is a multicriteria decision-making (MCDM) problem. TOPSIS is a widely used method for MCDM problem. We have used this method combined with intuitionistic fuzzy set to choose a suitable hotel. Finally, a numerical example with a case study of TripAdvisor.com is conducted for hotel selection to illustrate the function of intuitionistic fuzzy TOPSIS method.
... OCRs on hotels are considered an important source of travel information for customers, because OCRs increase potential customers' knowledge and improve their perceptions of travel products and they are considered and seen as an essential source of information (Memarzadeh & Chang, 2015). People tend to rely on information provided by OCRs in service sectors like hotels and restaurants, since it is not possible to visit and try these kind of products beforehand (Fang, Ye, Kucukusta, & Law, 2016). In order to reduce the risk, people need the opinions of others. ...
Article
Full-text available
Purpose – The aim of this research is to investigate the impact of Online Consumer Reviews (OCRs) on consumers’ online hotel booking intention in the hospitality sector in Turkey. Design / Methodology / Approach - This study utilizes quantitative research techniques. A self-administrated, 5 point Likert scale type online questionnaire was conducted in order to collect data. A total of 204 volunteer participants who were interested in online shopping, have participated in the survey. The research model consists of 7 independent and 2 dependent variables. While Review Source, Review Quality, Review Consistency, Review Volume, Review Recency, Negative Reviews and Positive Reviews are independent variables; Perceived Credibility of Online Consumer Reviews and Online Hotel Booking Intention are dependent variables. Confirmatory Factor Analysis (CFA) and Structural Equational Model (SEM) were utilized while analyzing the research model of the study. Findings – According to findings of the research, both positive and negative OCRs affect the perceived credibility of OCRs. However, there is no statistically significant impact found that review source, review recency, review consistency and review quality affect perceived credibility of OCRs. In addition, as per findings of the research, review volume and perceived credibility of OCRs have statistically significant impact on consumers’ online hotel booking intention. Discussion – People take into account other individuals’ opinions and comments when shopping online. This is particularly prominent in service sectors such as hotels that do not sell a tangible product. This study has investigated that the characteristics of OCRs influencing perceived credibility of OCRs and consumers’ online hotel booking intention. Perceived credibility was found to have a mediator role between characteristics of the OCR and online hotel booking intention. Findings of the study can be implemented by hotel brands in order to enhance customers’ online booking experience.
... The main element of a review is the review content. A review should be reliable or easy to understand without potential conflicts to provide information effectively [52]. ...
Article
Full-text available
Background: Patients face difficulties identifying appropriate physicians owing to the sizeable quantity and uneven quality of information in physician rating websites. Therefore, an increasing dependence of consumers on online platforms as a source of information for decision-making has given rise to the need for further research into the quality of information in the form of online physician reviews (OPRs). Methods: Drawing on the signaling theory, this study develops a theoretical model to examine how linguistic signals (affective signals and informative signals) in physician rating websites affect consumers' decision making. The hypotheses are tested using 5521 physicians' six-month data drawn from two leading health rating platforms in the U.S (i.e., Healthgrades.com and Vitals.com) during the COVID-19 pandemic. A sentic computing-based sentiment analysis framework is used to implicitly analyze patients' opinions regarding their treatment choice. Results: The results indicate that negative sentiment, review readability, review depth, review spelling, and information helpfulness play a significant role in inducing patients' decision-making. The influence of negative sentiment, review depth on patients' treatment choice was indirectly mediated by information helpfulness. Conclusions: This paper is a first step toward the understanding of the linguistic characteristics of information relating to the patient experience, particularly the emerging field of online health behavior and signaling theory. It is also the first effort to our knowledge that employs sentic computing-based sentiment analysis in this context and provides implications for practice.
... In terms of user evaluation, two indicators are used, one is the overall rating of products by consumers in the past and the other is the satisfaction of consumers on products. Following Fang et al. (2016), we include the mean of reviewers' historical ratings [81] of both indicators to measure the influence of the perceived value of online tourism reviews. The credit rating of a merchant is an indicator of the overall reputation of a merchant, which integrates the qualification, operation ability, user evaluation, stability of a merchant, and especially the compliance operation status. ...
Article
Full-text available
This study presents insights into the influence of the characteristics of tourism itineraries on tourist purchasing behavior. We adopted data between 1 August 2019 and 30 November 2019 from the Qunar, the biggest online tourism platform in China and 4366 samples on travel itineraries were obtained. The ordinary least square regression (OLS) method was used. Controlling for product-related and channel-related factors, we demonstrate that in terms of tourism destination choice, outbound tourism products attract an increased number of tourists; in terms of the types of travel, private travel has replaced group travel to become the majority of the tourism market; in terms of the length of travel, mid-term travel (4–6 days) is the first choice, outnumbering short-term and long-term ones; price promotions such as discount for early decision, multi-person price reduction and membership prices significantly lead to increased sales; online reviews also have great impact on tourist purchasing behavior. In sum, this study uses a unique data set to reveal the influence of online tourism product characteristics on sales and provide potential guidance of the marketing strategy in response to consumer behavior for the online tourism industry.
... Berger et al. (2010) even find that negative reviews also increase sales. Further, Fang et al. (2016) argue that reviews imbued with extreme sentiment are perceived as more valuable, while Babic Rosario et al. (2016) disprove this statement and believe that high variability in comments jeopardizes sales. The reasons for the problems in establishing volume and valence have been put forward by Ho-Dac et al. (2013), who suggest that the feedback loop for positive online reviews is created because negative online reviews are slower to be identified with than positive ones. ...
Article
Customer reviews and brand equity are both key assets that offer hospitality providers competitive advantages over rivalries. However, how they can complement each other is a question that scholars and practitioners continue to seek. This research draws on social identity and social presence theories to synthesize a multilevel model with social identification as a mediator of the relationship between persuasive message compliance and social commerce intention. We take a resource-based view to conceptualize brand equity as a strategic asset and to model it as a moderator. This inquiry contributes to extant literature by illuminating a multilevel paradigm to better understand the strategic imperative of brand equity in fortifying a strong brand, while casting means for weak brands to capitalize on e-WOM to impel favorable guest behaviors. It adds to the literature by acknowledging a dual-identification process in which both customer reviews and branding exercise different roles in customers' brand identification.
... Consumer empowerment has been strengthened with the advancements in the Internet (Pires et al., 2006). Consumers increasingly post their opinions/ experiences concerning products/services in the virtual space such as blogs, niche internet sites like TripAdvisor, Skytrax and social media such as Facebook, Twitter, and Instagram (Fang et al., 2016). This "digital footprint" left by consumers offers rich information such as consumer feedback, likes, dislikes, emotional polarity, and their repurchase intention (Sezgen et al., 2019). ...
Article
Full-text available
Using a mixed-method technique, the present study investigates the causal relationship between consumer judgments about airline service quality and their online recommendations. It also examines the essential attributes that determine key airline service quality dimensions. The current research was conducted on passenger reviews, ratings, and recommendations data (1270 business class and 2464 economy class passengers) from Skytraxratings.com of three major airlines using logistic regression and sentiment analysis. The empirical investigation of service ratings depicts that the fitted logit model adequately explains airline service quality-airline recommendation relationship for business and economy class travelers. Furthermore, this study identifies the crucial service attributes and their sentiment strengths toward key service dimensions. The study results enable a comprehensive understanding of airline service quality based on real-time consumer insights, which can help strategize and develop customized interventions for airline service designs and realignments.
... Prior research has been performed to analyze the determinants that affect RH concerning a review's content and context features. Content features are extracted from a review, such as review length [8,9], visibility [10,11], quality [12], linguistic style [13], and review emotions [9,14,15]. The context features include reviewer expertise [16,17] and review extremity [7,18]. ...
Article
Full-text available
Online physician reviews (OPRs) critically influence the patients’ consultation decisions on physician rating websites. The increasing number of OPRs contributes to the challenge of information overload. The worth of development needs to be explored further. Based on the OPRs collected from RateMDs and Healthgrades, and Plutchik’s wheel on human emotions framework, the purpose of this study was to examine the impact of emotional intensity (positive and negative) incorporated in OPRs on review helpfulness (RH). The proposed model was empirically tested using data from two physician rating websites and applying a mixed-methods approach (text mining and econometrics). The results suggested that anger, disgust, and fear (negative emotions), while joy, anticipation, and trust (positive emotions) significantly contributed to the perceived RH. Moreover, the patient’s disease severity moderated the association between negative emotions (anger and disgust), or positive emotions (joy and trust) and the perceived RH. Anger incorporated in an OPR has a more negative impact on perceived RH for severe diseases than the mild diseases. The findings contributed to the signif-icance of emotions in OPRs from an innovative perspective and provided practical insights for health rating platform owners to help patients in expressing their emotions more precisely.
... User-generated content, in the form of social media content, posts and online reviews, is increasingly relevant not only to understand more about consumers' opinions and preferences about travel, tourism and hospitality products, but also to generate business intelligence to improve products, services and attractions (Fang et al., 2016;Mariani and Borghi, 2021;Mariani et al., 2016;. The most popular form of BD from UGC is ORs, and the importance and function of these are examined in the next section. ...
... Liu et al. analyzed the impact of the number of comments, reviewer professionalism, reviewer reputation, and other factors on the usefulness of community online comments. In terms of the selection of influencing factors of comment usefulness, most of the existing studies consider the internal factors such as the star rating, number of comments, depth of comments, comment emotion, and external factors such as the identity, professionalism, and reputation of the comment publisher but few studies analyze the influencing factors from the professionalism of the comment content [11][12][13][14][15][16][17][18]. Because the comment information of each field contains its specific domain words, there are serious domain barriers. ...
Article
Full-text available
With the increasing application of the perceptron genetic algorithm neural network in Chinese-English two-way translation, there are many translation problems to be solved. In order to solve the translation problem of Chinese-English parallel corpus, the multilayer perceptron method, genetic word alignment model (GA), language model, and neural network method (including the translation model and bilingual pretraining model) are designed, which are combined into the ga-mlp-nn combination model to measure the parallelism of Chinese and English sentences from different emphases. The results show that the ga-mlp-nn model has good performance in filtering high-quality parallel corpus. The final experimental results show that compared with a single system, the improved multisystem fusion method based on weight multiplication has achieved better results in the test set. In the last five groups of evaluation results, the system submitted in this paper ranks second and first in multiple datasets, which has a certain reference value for the research of corpus filtering.
... Often the hotel category is a method used by consumers to select a hotel (Núñez-Serrano et al., 2014). Furthermore, the hotel quality can be inferred from their stars (Fang, Ye, Kucukusta, & Law, 2016). ...
Conference Paper
Full-text available
Globally, the Muslim population is growing and if current trends continue, Muslims will make up 26.4% of the world’s total projected population of 8.3 billion in 2030. This worldwide growth of the Muslim population in the middle class and younger population has meant that Muslim tourists are becoming a significant segment within the global travel and tourism sector. According to the latest statistics total Muslim tourist arrivals were 116 million in 2014 and the Islamic Republic of Iran, despite having 7th rank in terms of Muslim tourist arrivals with 4.1 million total Muslim tourist arrivals, was in the 11th rank in terms of Islamic and Halal tourism receipts with US$ 942.5 million recorded in 2014. Sub-optimal place of Iran in Islamic and Halal tourism market as one of the most important Islamic countries, its low share of this highly profitable market despite possessing maximum Muslim population and an Islamic government with high compatibility of this type of tourism with its socio-cultural and religious values and norms, depicts the importance of this newfound type of tourism as one of the most appropriate options for tourism industry development in Iran and necessity of paying attention to its high potential in this countries tourism planning and policy-making process.
... The main contents of the framework are as follows: (1) Linguistics and sufficiency: in information science and communication studies, the linguistic features used to measure the quality of review text mainly include features such as the number of comments, comment length (i.e., number of words), timeliness, relevance, and completeness (Bailey & Pearson, 1983). Among these features, the number of comments (Filieri & Mcleay, 2014;Liu & Park, 2015;Zhang, Ye, Law, & Li, 2010) and comment length (Chevalier & Mayzlin, 2006;Fang, Ye, Kucukusta, & Law, 2016;Liu & Park, 2015) are important indicators of the linguistic characteristics of the comments, and they significantly affect the credibility of the reviews. The number and credibility of reviewers also influence consumers' trust in reviews and websites (Cheung, Luo, Sia, & Chen, 2009;Filieri et al., 2015;Levy, Duan, & Boo, 2013;Liu & Park, 2015). ...
Article
Full-text available
This thematic analysis examines whether reviews on transactional and social media websites can reflect the air quality of a tourist destination. We used linguistic and sentiment analysis methods to establish an analytical framework for assessing the credibility of the reviews with sufficiency and consistency analyses. We collected Ctrip and Sina Weibo reviews to analyze the sentiment values using deep learning and Baidu sentiment dictionary methods. We found that although the sentiment value of the Ctrip transactional comments on air quality was high, they hardly reflected reality. Conversely, the Sino Weibo social media comments were highly credible, despite their low sentiment values. Tourists' perception of air quality is not only mainly affected by intangible factors such as pollutants but also by tangible factors such as blue sky. The study uses online reviews to analyze air quality and provides a reference for the environmental management of destinations and decision making among tourists.
... This study reveals that big data analytics can produce new insights into variables that have been broadly studied in existing hospitality. (Fang, Ye, Kucukusta, & Law, 2016) "Analysis of the perceived value of online tourism reviews: Influence of readability and reviewer characteristics" Tourism Management ...
Article
Full-text available
Tourism research has marched into the big data arena and brought remarkable developments. Despite the promising role of big data and increasing volume of research, it is worth noting that current big data research in the tourism and hospitality field is rather vague or insufficient, particularly from the perspectives of its philosophical grounding, methodological approaches, and implications. This article aims to provide a comprehensive review of big data research from the tourism and hospitality literature. A content analysis of 146 big-data-related articles identifies the research and methodological trends in these fields. The findings reveal that big data have expanded the scope of tourism research. It offers useful and practical knowledge for destination, hotel, revenue, and reputation management. However, big data research is rather limited in methodologies, and there is a need for more solid theoretical and philosophical footings for significant knowledge generation.
... Consumers view online reviews to be less biased and more trustworthy (Vermeulen and Seegers, 2009). Fang et al. (2016) defined online reviews as "numerical ratings and descriptive comments provided by current and past customers which are used to express satisfaction or dissatisfaction, often submitted with opinions or recommendations, revolving around an experience with a product or service." Mauri and Minazzi (2015) confirm the importance of online reviews valence in their study of the Italian hotel industry. ...
Article
Full-text available
Purpose The COVID-19 pandemic has resulted in significant changes in tourists’ attitudes and behaviors mostly as a result of confinement-related problems. Although various studies have been conducted to analyze customers’ perceptions of service quality and satisfaction using a drop-off/pick-up method, the influence of COVID-19 on customers’ perceptions of service quality and satisfaction has not been examined using online reviews. It is critical to evaluate satisfaction aspects from user-generated content to ascertain their preferences for hotel services during the pandemic. This research aims to explore the viewpoint shared online by hotel tourists, as well as identify which service practice is associated with higher and lower satisfaction during the COVID-19 pandemic.
Article
Purpose The importance of online reviews on online hotel booking has been widely acknowledged. However, not all online reviews affect consumers equally. Compared with common online reviews, key online reviews (KORs) have a greater influence on consumers' decisions and online hotel booking. This study takes the first step to investigate the factors affecting the identification of KORs and the role of KORs in online hotel booking. Design/methodology/approach To test the research hypotheses, this study develops a crawler to obtain 551,600 online reviews of 650 hotels in ten representative large cities in China. This study first uses a binary logistic regression to identify KORs by combining review content quality and reviewer characteristics and then uses a log-regression model to investigate the role of KORs in online hotel booking. Findings This study mined the factors affecting the identification of KORs by analyzing review contents and reviewer characteristics. Our results revealed that KORs play a mediating role in the effects of review content and reviewer characteristics on online hotel booking. Originality/value This study focuses on KORs, which have received limited attention in research but are important to practitioners. Specifically, this study investigates the antecedents and consequences of KORs. Our results enable hotel managers to manage online reviews effectively, particularly KORs.
Article
Full-text available
Purpose Drawing on attribution theory, the current paper aims to examine the effects of review content structures on online review helpfulness, focusing on three pertinent variables: review sidedness, information factuality, and emotional intensity at the beginning of a review. Moreover, the moderating roles of reviewer reputation and review sentiment are investigated. Design/methodology/approach The review sentiment of 144,982 online hotel reviews was computed at the sentence level by considering the presence of adverbs and negative terms. Then, the authors quantified the impact of variables that were pertinent to review content structures on online review helpfulness in terms of review sidedness, information factuality and emotional intensity at the beginning of a review. Zero-inflated negative binomial regression was employed to test the model. Findings The results reveal that review sidedness negatively affects online review helpfulness, and reviewer reputation moderates this effect. Information factuality positively affects online review helpfulness, and positive sentiment moderates this impact. A review that begins with a highly emotional statement is more likely to be perceived as less helpful. Originality/value Using attribution theory as a theoretical lens, this study contributes to the online customer review literature by investigating the impact of review content structures on online review helpfulness and by demonstrating the important moderating effects of reviewer reputation and review sentiment. The findings can help practitioners develop effective review appraisal mechanisms and guide consumers in producing helpful reviews.
Article
Purpose To examine the relationship between online comments, merchant replies and online sales of tourism products and focus on the moderating role of tourist destination. Design/methodology/approach This article uses crawler technology and regression analysis methods. Findings The researchers found the following: (1) The number of pictures uploaded with online comments, the number of merchant replies and the length of merchant replies have a significant positive effect on sales of tourism products, while the length of comments and the similarity of merchant replies negatively affect sales of tourism products. The emotional scores of the reviews do not significantly affect sales of tourism products. (2) Tourist destination moderates the relationship between user comments and sales of tourism products. The length of comments has a greater negative effect on sales of domestic tourism products, while the number of comments has a greater positive effect on sales of overseas tourism products. (3) Tourist destination moderates the relationship between merchant replies and sales of tourism products. Consumers who choose domestic tourism products pay more attention to the interactivity reflected by merchant replies (e.g. number and length of merchant replies), while consumers who choose overseas tourism products hope to receive replies that are more useful, such as reply similarity. Originality/value The research conclusions enrich the relevant research in the field of online review research and has practical significance for how companies increase sales of tourism products.
Purpose The length of stay (LoS) is of major importance from the perspective of the management of tourist destinations. As tourists heavily rely on the online reviews of other travelers as a primary information source, this study aims to empirically examine how the LoS can influence the online reviews for hotels, with special emphasis on the textual review content. Design/methodology/approach This study analyzes online review data collected from Booking.com by using the Linguistic Inquiry and Word Count program to operationalize review depth, analytical thinking and the authenticity reflected in customer reviews. Based on the analyzed data, this study used a series of regression analyses to understand the impacts of the LoS on online reviews. Findings The author’s analysis found that a longer stay at a hotel causes consumers to be more likely to post online reviews that not only include a numerical rating as well as written content but also lengthier and more detailed descriptions of their hotel experiences. Further analysis found that the LoS at hotels causes systematic differences in the linguistic attributes of the review content. Specifically, consumers who stay longer tend to write reviews with more analytical information, resulting in consumers perceiving the online reviews as more authentic. Research limitations/implications Although the LoS has been considered a significant issue in tourism, studies examining the impact of different lengths of stay on consumers’ post-purchase behaviors are limited. In this light, the author’s findings demonstrate how the LoS can change the linguistic attributes of online reviews. It expands the body of knowledge of the LoS in tourism. Originality/value This study represents the first attempt to empirically examine and reveal how the different length of stay at a hotel systemically influences consumer review-posting behaviors.
Article
This study aims to forecast international tourist arrivals to Hong Kong from seven English-speaking countries. A new direction in tourism demand modeling and forecasting is presented by incorporating tourist-generated online review data related to tourist attractions, hotels, and shopping markets into the destination forecasting system. The main empirical findings indicate that tourism demand forecasting based on tourists’ online review data can substantially improve the forecasting performance of tourism demand models; specifically, mixed data sampling (MIDAS) models outperformed competing models when high-frequency online review data were included in traditional time-series models.
Article
In natural language processing, text classification is a fundamental problem. Multi-label classification of textual data is a challenging topic in text classification where an instance can be associated with more than one label. This paper presents a multi-label annotation and classification methodology for Arabic text data that is not currently classified as multi-label, aiming to analyze and compare the performance of various multi-label learning approaches. The current work includes two phases: The first involves automatic annotation of hotel reviews with more than one label based on the aspects found in the reviews. In this phase, review data instances were automatically annotated as multi-label based on the extracted seed keyphrases clusters. The second phase involves experiments to compare the performance of various multi-label classification learning methods. In this phase, we introduced different models including feed-forward networks model that learns a vector representation based on the bi-gram alphabet rather than the commonly used bag-of-words model. The bi-gram alphabet vector representation model has the advantage of having reduced feature dimensions and not requiring natural language processing tools. The results indicated that employing the bi-gram alphabet vector representation feed forward neural network is a competitive solution for the multi-label text classification problem. It has achieved an accuracy of about 75.2%, and standard deviation (0.062).
Purpose This paper aims to examine the impact of selected characteristics (rating, volume and variability) of online user-generated reviews on the bottom-line profitability of restaurants. Design/methodology/approach Restaurant-level review data are extracted from TripAdvisor and matched with firm-level data from the financial reports gathered from the Belfirst database of Bureau van Dijk. The resulting sample contains data on 2,297 Belgian firms over the period 2007–2018, for which 134,831 reviews are investigated. The author’s regression model of firm-level profitability is estimated against online review characteristics and various financial control variables, including past profitability. This research model and estimation technique address the endogeneity concerns that typically weaken this kind of study. Findings While comparable studies on hotels document a positive association between review characteristics and profitability, the authors find no relationship between review rating, volume and variability in the profitability of restaurants. Research limitations/implications Due to the format of the financial reports of small and medium-sized enterprises (SMEs), data on turnover and cost of materials/services was not available for most restaurants in the sample, limiting our potential for analysis. In addition, our assessment of electronic word of mouth (eWOM) was limited to measures derived from user-generated reviews on TripAdvisor. Practical implications In the literature on eWOM, the importance of online reputation is hardly disputed, especially in the context of the hospitality sector. However, most research to date has focused on the hotel sector and top-line measures of success. This study uses restaurant-level financial data, focuses on bottom-line profitability, considers potential endogeneity issues and pays careful attention to the estimation technique. The results fail to establish a direct relationship between eWOM metrics and financial performance and are surprising, meriting further investigation to establish the underlying causes. Originality/value In contrast to prior studies on the impact of eWOM on restaurant performance at a group level, this study examines the impact on unit-level profitability, taking into account several potential sources of estimation bias. In addition, the authors challenge this finding with a battery of sensitivity tests, revalidating the absence of a relationship in each case.
Article
Electronic word-of-mouth (eWOM) communication on social media has revolutionized how travelers search for and share information and how they interact with one another digitally. This research examines the effects of eWOM-triggered customer-to-customer (C2C) interactions on travelers’ post-eWOM behaviors (i.e., repurchase and customer engagement) in a cross-cultural context. Drawing upon cognitive dissonance theory, a scenario-based experiment was conducted using a sample of 461 African tourists with recent intracontinental travel experience. Our findings suggest that a customer’s repurchase intention and engagement in social media C2C interactions are significantly influenced when their eWOM is challenged by other customers. Compared with individualistic cultures, such a phenomenon is more effective in collectivistic cultures, particularly when a customer shares negative eWOM. Customers in collectivistic cultures are more likely to appreciate consensus with other customers, and they tend to expend more effort toward solving dissonance. The theoretical and managerial implications of these findings are discussed.
Article
Online consumer reviews significantly impact market performance as potential customers rely heavily on these reviews for consumer decision making. Accordingly, experienced online reviewers, or highly motivated reviewers who account for the largest attribution of reviews, are proposed to be an important part of the online reviewing ecosystem. This research examines experienced reviewers in the online communities. Using empirical data, this study found that experienced reviewers tend to behave as experts with the aim to achieve a common good with rating and selection attributes similar to critics. Hence, results showed that experienced reviewers leave lower ratings, have less extremity in their ratings, prefer sophisticated products but do not prefer popular products. The female experienced reviewers are less generous than novice female reviewers and their generosity decreases more dramatically than males in the rating propensity as they become experienced reviewers.
Article
Given strong influences of online customer reviews on consumer purchase decisions, identifying helpful reviews has received broad attention from practitioners and researchers. The elaboration likelihood model (ELM) has been adopted to explain the review feature–helpfulness link. However, when analyzing reviews from websites, existing studies tend to ignore that quality indicators such as length and readability are merely cues and have not circumvented endogeneity induced by unseen argument quality. Hence, we propose an extended ELM application to observational data on review helpfulness. We develop a research model that integrates relevant quality indicators and sentiment features based on a circumplex model of affect. To test our hypotheses, we use publically available review datasets from three platforms (Amazon.com, Drugs.com, and Yelp.com) and adopt an instrument-free method that allows for arbitrary correlations between unseen argument quality and multiple endogenous indicators. Our analysis shows that ignoring endogeneity would result in invalid effect size and hypothesis-testing. In addition to identifying effects of endogenous quality indicators on review helpfulness, we find asymmetric effects of positive and negative valence contingent on low or high arousal. By articulating conceptual pitfalls and illustrating empirical remedies, our study aims to be a prototypical example of performing ELM-grounded analyses of online customer reviews.
Article
Managerial response describes how hotel managers communicate with online reviewers and manage their customer relationships. The purpose of this study is to examine the moderating effect of managerial response on the relationship between review characteristics and review helpfulness. Based on cue utilization theory, this study employs the negative binomial regression to analyse data from TripAdvisor.com. The study results indicate the extrinsic cues (managerial response length and response speed) moderate the effect of intrinsic cues (review sentiment and review length) on review helpfulness. The negative effect of review sentiment on helpfulness is weakened as response length and speed increase; the positive effect of review length on helpfulness is enhanced when response speed is fast, whereas this impact is weakened as response length increases. This study also discusses practical significance for hotel managers, consumers, and online travel platforms.
Article
Humans in hospitality areas are being replaced by robot concierges, delivery robots, chatbots, and information assistants through a variety of devices, for example, mobile apps and self-service check-in/check-out machines. Powered by artificial intelligence (AI) algorithms, big data, mobile Internet and internet-of-things technologies, inventions supporting a sustainable shift to social robotics have recently been growing exponentially. Despite this unidirectional movement, there has been a lack of effort to monitor customer responses regarding specific situations in a timely manner. In this study, we examine YouTube, an online streaming video website, to uncover what factors affect attitudes towards RAISA (Robot, AI, and Service Automation) applications in the hospitality industry. The findings show that the sentiment of the content of video narration and physical interaction influence potential customer attitudes toward RAISA services in hospitality. This study provides insights about how online buzz can offer an initial reference for potential customers to deal with the uncertainty of innovative services and provide practitioners with information about proper design guidelines for promoting RAISA applications to their businesses by grasping the trend of broad opinion in real time.
Article
Purpose The current study employs text mining and sentiment analysis to identify core banking service attributes and customer sentiment in online user-generated reviews. Additionally, the study explains customer satisfaction based on the identified predictors. Design/methodology/approach A total of 32,217 customer reviews were collected across 29 top banks on bankbazaar.com posted from 2014 to 2021. In total three conceptual models were developed and evaluated employing regression analysis. Findings The study revealed that all variables were found to be statistically significant and affect customer satisfaction in their respective models except the interest rate. Research limitations/implications The study is confined to the geographical representation of its subjects' i.e. Indian customers. A cross-cultural and socioeconomic background analysis of banking customers in different countries may help to better generalize the findings. Practical implications The study makes essential theoretical and managerial contributions to the existing literature on services, particularly the banking sector. Originality/value This paper is unique in nature that focuses on banking customer satisfaction from online reviews and ratings using text mining and sentiment analysis.
Article
This study examines the adaptive reuse of an abandoned heritage ensemble, Sa'd al-Saltaneh Caravanserai, in Qazvin, Iran, through ‘place making’, a multifaceted approach to create urban spaces. We applied a qualitative research approach, focusing on in-depth semi-structured interviews and on-site observations. The findings revealed that the adaptive reuse project and place making had created a positive image of the city and a popular place for citizens and tourists to visit. The results support the assertion that tourism place making, using arts and culture, could be a helpful way for heritage conservation in long-neglected historical centers and improve the image and experiences of urban places. However, the neglect of the community needs in the process of place making may hinder the realization of effective urban regeneration and sustainable tourism development. Through the case of Qazvin, we argue that the lack of a comprehensive and multidimensional approach in the process of tourism place making can worsen the situation for residents and eliminate the residential role of central neighborhoods. The study contributes to the literature on heritage adaptive reuse and tourism place making from the perspectives of different groups of stakeholders.
Article
Full-text available
This paper proposes a framework for hotel selection based on online reviews by sentiment analysis from the perspective of consensus group decision making. To identify multi-granularity sentiment strength in text reviews, a sentiment analysis method based on the Word2Vec algorithm and one-vs-one strategy based Support Vector Machine (OVO-SVM) algorithm is provided. Then, richer information content can be derived from online text reviews, which are used as the data source of this study. To help members make an aggregation on the preference of hotel attributes, a consensus model with an improved feedback mechanism is proposed, which can reasonably control the adjustment cost in the consensus reaching process. Combining the hotel performance obtained from online reviews and the group preference consensus, the optimal hotel for members can be selected. At the end of this paper, a case study is presented to illustrate the use of the proposed method.
Article
Tourism has become a growing industry day by day with the developing economic conditions and the increasing communication and social interaction ability of the people. Forecasting tourism demand is not only important for tourism operators to maximize their revenues but also important for the formation of economic plans of the countries on a global scale. Based on the predictions countries are able to regulate the sectors that benefit economically from tourism locally. Therefore, it is crucial to accurately predict the demand in many weeks advance. In this study, we propose a new demand forecasting model for the hospitality industry that forecasts weekly hotel demand four weeks in advance through Attention-Long Short Term Memory (Attention-LSTM). Unlike most of the existing methods, the proposed method utilizes the time series demand data together with additional features obtained from K-Means Clustering findings such as Top 10 Hotel Features or Hotel Embeddings obtained using Neural Networks (NN). While creating our model, the clustering part was influenced by the fact that travelers choose their accommodation according to certain criteria, and the hotels meeting similar criteria may have similar demands. Therefore, before the clustering part, we also applied methods that would enable us to represent the features of the hotels more properly and we observed that 10-D Embedded Hotel Data representation with NN Embeddings came to the fore. In order to observe the performance of the proposed hotel demand forecasting model we used a real-world dataset provided by a tourism agency in Turkey and the results show that the proposed model achieves less mean absolute error and mean absolute percentage error (at worst % 3 and at most % 29 improvements) compared to the currently used machine learning and deep learning models.
Article
Purpose The conclusions of studies on the factors correlated with the perceived usefulness of online reviews are inconsistent due to differences in research perspectives, research objects, research methods and data types. This study conducted a meta-analysis to verify a proposed model of perceived usefulness to obtain general conclusions. Design/methodology/approach A meta-analysis was conducted to study the factors correlated with the perceived usefulness of online reviews based on 51 studies. Findings The results indicate that, with the exception of negative reviews, the order of relevance for the perceived usefulness of online reviews is as follows: the trust tendency of review readers, review replies, review depth, review pictures, reviewer trustworthiness, positive reviews, reviewer expertise, review time and reviewer information disclosure. Perceived usefulness was significantly positively correlated with purchase intention. Review time, positive reviews and negative reviews were also more significantly correlated with perceived usefulness for search products than for experiential products. Review depth, reviewer trustworthiness, reviewer expertise and purchase intention had greater positive correlations with perceived usefulness for experiential products than for search products. Originality/value This study proposes an extended information adoption model based on argument quality and source credibility. The model includes personal factors such as the trust tendency of review readers, constructs a theoretical model of the factors correlated with the perceived usefulness of online reviews and considers the moderating effects of product type.
Article
Purpose This research aims to classify and describe food festivals and examine the patterns in food festival naming and festival descriptions in online media. Design/methodology/approach This research represents the first population-level empirical examination of food festivals in the United States using a purpose-built dataset ( N = 2,626). Methodology includes text mining to examine food festival communications. Findings Food festival size varies across local and regional spheres within the country. Food festivals employ geographical (place-, destination-based) associations in their names. Food festivals' descriptions and online communications showcase a welcoming environment predominantly emphasizing family-oriented and live entertainment experiences. Food festivals across the country show common naming patterns based on the elements of longevity, recurrence, location name, brand name, geographic scope, theme, and occasion. Originality/value The study makes an original contribution to the theory and practice by identifying festival forms, styles, functions, and their diversity. A population level examination of food festivals does not currently exist. Therefore, this research will serve as a foundation for scholarly work in the future and as a benchmark for evaluating current and future research.
Article
Full-text available
The intercultural nature of tourism makes interpersonal communication a critical element that influences individuals’ experience and, in turn, their satisfaction. The existing research predominantly focuses on indirect communication (such as advertising). This study contributes to the literature by examining the effect of the reviews of language use on overall satisfaction and by looking into the dyad formed by the extreme vs. moderate character of the reviews and their sign (positive vs. negative). The analysis of 48,491 online reviews shows the effect of language use opinions on overall satisfaction, with extreme opinions having a more significant impact than moderate opinions. A more interesting and relevant impact is the departure from the well-established cognitive negativity bias characteristics of online reviews: extreme reviews have a symmetric impact on satisfaction, and moderate reviews present asymmetric effects. Both outcomes are a deviation from this cognitive bias, and relevant implications are derived.
Article
Full-text available
The objective of this study is to evaluate the key attributes of Busan luxury hotels through text mining which customers perceive as a means of satisfaction and provide implications based on the results of the findings. The research was conducted by SCTM (Smart Crawling & Text Mining) 3.0 from 7 different luxury hotels of Busan, where 25,039 reviews were collected from google travel (www.google.com/travel) for further study purposes. Data period was from September 2016 to September 2021 (5 years). Data analysis result illustrated top 49 words which were extracted from online review. Semantic network analysis was conducted for revealing word network using UCINET 6.0. Further, CONCOR (CONvergence of iterated CORrelation) analysis, keywords were divided into four different clusters named as “Facility”, “Food & Beverage”, “Service” and “Theme”. From the finding, theoretical and practical implication was provided for the improving of service and facilities of luxury hotel of Busan to enhance better customer satisfaction. The result shows, four clusters can be counted as a key attribute for customer satisfaction in Busan luxury hotels where these clusters can also be taken into consideration for enhancing and improving their overall service and facilities.
Article
With the development of internet, online reviews are user-generated content posted in we-media era and can extract meaning from the comments through data-mining technology. The study uses python crawler to collect reviews and conduct post-occupancy evaluation on Oze National Park (ONP), a natural conservation in Japan. Content and semantic network analysis were adopted to study the high frequency words and their relationships. Latent Dirichlet Allocation was utilized to uncover the dimensions of the comments. The conclusions were as follows: 1) Japanese tourists focused on landscape plants and nature, while the Chinese focused on facilities and experience, English concentrated on hiking activity. 2) The Ozegahara Plateau route and the Lake Ozenuma route were the two main courses in ONP. 3) 48% of the concept of the landscape of ONP was conveyed to the users. 4) Male tourists focused on location information and landscape, while females were concerned about the process and experience. The single-visitors paid attention to the road and boardwalk. Family tourism concentrated on experience and time while friends and couple-visitors preferred to perceive action. 5) The Lysichiton Americanus had become a basic feature of ONP, and visitors were satisfied with the landscape and experience.
Article
For hotels, strengthening their relationships with customers to build loyalty and encourage them to become repeat patrons enhances their financial performance. Online managerial response (MR) is an effective means for hoteliers to interact with customers and attract return customers. This study examines how the linguistic characteristics of MRs in five dimensions—sentiment polarity, subjectivity, diversity, length, and readability—affect return customers’ change in satisfaction. We find that, for primary dissatisfied customers, diversity and sentiment polarity of MRs decrease customers’ incremental satisfaction during their second visit. For primary satisfied customers, MRs’ readability positively affects customers’ second-time incremental satisfaction, whereas sentiment polarity negatively affects it. The subjectivity and length of MRs do not have a significant effect on return customers’ satisfaction change. Our findings provide guidelines for hotel managers on how to write responses to customer reviews with a linguistic style that enhances customers’ retention and subsequent satisfaction upon revisiting.
Article
Full-text available
Consumer-generated content (CGC) is growing in importance. Especially online travel reviews written by consumers are ever more available and used to inform travel-related decisions. A Web-based survey of users of the most prominent travel review site, TripAdvisor, was conducted to investigate how other travellers' reviews inform the trip planning process. Since current CGC statistics show generational and gender differences, the study also aimed at examining whether those carry over into the realm of travel review use. The results show that reviews are used mostly to inform accommodation decisions and are currently not used much for en route travel planning. Gender differences were found for perceived impacts of reviews, with females reaping greater benefits from using reviews, especially in terms of enjoyment and idea generation. Age differences occurred across a variety of perceptions and use behaviours. Implications for travel marketing and travel information systems design are provided. Keywords: online travel reviews; consumer generated content; trip planning; age differences; gender differences.
Article
Full-text available
This study presents the results of an initial phase of a project seeking to convert texts into a more accessible form for people with autism spectrum disorders by means of text simplification technologies. Random samples of Simple Wikipedia articles are compared with texts from News, Health, and Fiction genres using four standard readability indices (Kincaid, Flesch, Fog and SMOG) and sixteen linguistically motivated features. The comparison of readability indices across the four genres indicated that the Fiction genre was relatively easy whereas the News genre was relatively difficult to read. The correlation of four readability indices was measured, revealing that they are almost perfectly linearly correlated and that this correlation is not genre dependent. The correlation of the sixteen linguistic features to the readability indices was also measured. The results of these experiments indicate that some of the linguistic features are well correlated with the readability measures and that these correlations are genre dependent. The maximum correlation was observed for fiction.
Chapter
Full-text available
Virtual communities rely on active and committed members who make regular contributions. These contributors typically get psychological and social rewards for their virtual community activities. Given their importance for community sustainability, it is essential for community platforms to understand who their most active members are and what status seeking strategies they employ. This research looks at TripAdvisor and its dedicated Destination Experts to examine how localized the expertise is in this community, how the community acknowledges expertise, whether status seeking strategies can be detected, and if the Destination Experts differ from general reviewers. The findings reveal that Destination Experts are active throughout the TripAdvisor platform and are indeed important and influential pillars of the community.
Article
Full-text available
While the proliferation of online review websites facilitate travellers' ability to obtain information (decrease in search costs), it makes it difficult for them to process and judge useful information (increase in cognitive costs). Accordingly, this study attempts to identify the factors affecting the perceived usefulness of online consumer reviews by investigating two aspects of online information: (1) the characteristics of review providers, such as the disclosure of personal identity, the reviewer's expertise and reputation, and (2) reviews themselves including quantitative (i.e., star ratings and length of reviews) and qualitative measurements (i.e., perceived enjoyment and review readability). The results reveal that a combination of both messenger and message characteristics positively affect the perceived usefulness of reviews. In particular, qualitative aspects of reviews were identified as the most influential factors that make travel reviews useful. The implications of these findings contribute to tourism and hospitality marketers to develop more effective social media marketing.
Article
Full-text available
The quality of service received from an e-auction website owes much to the use of self-service technology. Researchers have proposed that user personality traits and user perceptions of the service provider have an impact on individual use of web-based technology. This paper describes the development and validation of a conceptual model illustrating the impact of both the personality trait of technology readiness and the perception of online service provider trustworthiness on intentions to continue with the service. Using survey data collected from e-auction users in China and employing SEM analysis procedures, we found that both technology readiness and perceived service provider trustworthiness had an impact on user satisfaction of e-auction services which, in turn, had an impact on intentions to continue with the e-auction services. Implications and future research directions are also included in the study.
Article
Full-text available
User-generated content on social media platforms and product search engines is changing the way consumers shop for goods online. However, current product search engines fail to effectively leverage information created across diverse social media platforms. Moreover, current ranking algorithms in these product search engines tend to induce consumers to focus on one single product characteristic dimension (e.g., price, star rating). This approach largely ignores consumers' multidimensional preferences for products. In this paper, we propose to generate a ranking system that recommends products that provide, on average, the best value for the consumer's money. The key idea is that products that provide a higher surplus should be ranked higher on the screen in response to consumer queries. We use a unique data set of U.S. hotel reservations made over a three-month period through Travelocity, which we supplement with data from various social media sources using techniques from text mining, image classification, social geotagging, human annotations, and geomapping. We propose a random coefficient hybrid structural model, taking into consideration the two sources of consumer heterogeneity the different travel occasions and different hotel characteristics introduce. Based on the estimates from the model, we infer the economic impact of various location and service characteristics of hotels. We then propose a new hotel ranking system based on the average utility gain a consumer receives from staying in a particular hotel. By doing so, we can provide customers with the "best-value" hotels early on. Our user studies, using ranking comparisons from several thousand users, validate the superiority of our ranking system relative to existing systems on several travel search engines. On a broader note, this paper illustrates how social media can be mined and incorporated into a demand estimation model in order to generate a new ranking system in product search engines. We thus highlight the tight linkages between user behavior on social media and search engines. Our interdisciplinary approach provides several insights for using machine learning techniques in economics and marketing research.
Article
Full-text available
With the rapid growth of the Internet, the ability of users to create and publish content has created active electronic communities that provide a wealth of product information. However, the high volume of reviews that are typically published for a single product makes harder for individuals as well as manufacturers to locate the best reviews and understand the true underlying quality of a product. In this paper, we reexamine the impact of reviews on economic outcomes like product sales and see how different factors affect social outcomes such as their perceived usefulness. Our approach explores multiple aspects of review text, such as subjectivity levels, various measures of readability and extent of spelling errors to identify important text-based features. In addition, we also examine multiple reviewer-level features such as average usefulness of past reviews and the self-disclosed identity measures of reviewers that are displayed next to a review. Our econometric analysis reveals that the extent of subjectivity, informativeness, readability, and linguistic correctness in reviews matters in influencing sales and perceived usefulness. Reviews that have a mixture of objective, and highly subjective sentences are negatively associated with product sales, compared to reviews that tend to include only subjective or only objective information. However, such reviews are rated more informative (or helpful) by other users. By using Random Forest-based classifiers, we show that we can accurately predict the impact of reviews on sales and their perceived usefulness. We examine the relative importance of the three broad feature categories: “reviewer-related” features, “review subjectivity” features, and “review readability” features, and find that using any of the three feature sets results in a statistically equivalent performance as in the case of using all available features. This paper is the first study that integrates eco- - nometric, text mining, and predictive modeling techniques toward a more complete analysis of the information captured by user-generated online reviews in order to estimate their helpfulness and economic impact.
Article
Full-text available
Online word-of-mouth (WOM) such as consumer opinions, user experiences, and product reviews has become a major information source in consumer purchase decisions. Prior research on online WOM effect has focused mostly on low-involvement products such as books or CDs. For these products, retailer-hosted (internal) WOM is shown to influence sales overwhelmingly. Numerous surveys, however, suggest consumers often conduct pre-purchase searches for high-involvement products (e.g., digital cameras) and visit external WOM websites during the search process. In this study, we analyze the relative impact of external and internal WOMs on retailer sales for high-involvement products using a panel of sales and WOM data for 148 digital cameras from Amazon.com and three external WOM websites (Cnet, DpReview, and Epinions) over a four-month period. The results suggest that a retailer's internal WOM has a limited influence on its sales of high-involvement products, while external WOM sources have a significant impact on the retailer's sales. The findings imply that external WOM sources play an important role in the information search process.
Article
Full-text available
Detecting low observable targets within sea clutter at low grazing angle is one of the research hotspots in radar signal processing community. In this paper, we have proposed a novel method based on polarimetric decomposition theorem. The polar characteristics of sea clutter has been analyzed, with the parameters after the decomposition of target scattering matrix. The scattering entropy and the scattering angle are the key parameters to discriminate the target from the sea clutter. The technique is designed to suppress unwanted sea clutter at polarimetric domain. Datasets from real marine radar are used to illustrate the performance of the new approach.
Article
Full-text available
This article investigates the main and interactional effects of review valence and the presence of source identity on consumer perception of credibility of an online review and initial trust of travel services being reviewed. An experimental design is developed involving 639 travel consumers. Results indicate that a negative online review is deemed more credible than a positive online review, while a positive online review leads to a greater initial trust than a negative review. These findings apply when the identity of the reviewer is disclosed. However, when the reviewer’s identity is not disclosed, there is no significant difference between positive and negative reviews either in terms of perceived credibility or impact on consumer trust. Theoretical and managerial implications, limitations and future directions are also discussed.
Article
Full-text available
Online reviews have received much attention recently in the literature, as their visibility has been proven to play an important role during the purchase process. Furthermore, recent theoretical insight argue that the votes casted on how helpful an online review is (review helpfulness) are of particular importance, since they constitute a focal point for examining consumer decision making during the purchase process. In this paper, we explore the interplay between online review helpfulness, rating score and the qualitative characteristics of the review text as measured by readability tests. We construct a theoretical model based on three elements: conformity, understandability and expressiveness and we investigate the directional relationship between the qualitative characteristics of the review text, review helpfulness and the impact of review helpfulness on the review score. Furthermore, we examine whether this relation holds for extreme and moderate review scores. To validate this model we applied four basic readability measures to a dataset containing 37,221 reviews collected from Amazon UK, in order to determine the relationship between the percentage of helpful votes awarded to a review and the review text’s stylistic elements. We also investigated the interrelationships between extremely helpful and unhelpful reviews, as well as absolutely positive and negative reviews using intergroup comparisons. We found that review readability had a greater effect on the helpfulness ratio of a review than its length; in addition, extremely helpful reviews received a higher score than those considered less helpful. The present study contributes to the ever growing literature on on-line reviews by showing that readability tests demonstrate a directional relationship with average length reviews and their helpfulness and that this relationship holds both for moderate and extreme review scores.
Article
Full-text available
Despite hospitality and tourism researchers’ recent attempts on examining different aspects of online word-of-mouth [WOM], its impact on hotel sales remains largely unknown in the existing literature. To fill this void, we conduct a study to empirically investigate the impact of online consumer-generated reviews on hotel room sales. Utilizing data collected from the largest travel website in China, we develop a fixed effect log-linear regression model to assess the influence of online reviews on the number of hotel room bookings. Our results indicate a significant relationship between online consumer reviews and business performance of hotels.
Article
Full-text available
The authors investigate how critics affect the box office performance of films and how the effects may be moder- ated by stars and budgets. The authors examine the process through which critics affect box office revenue, that is, whether they influence the decision of the film going public (their role as influencers), merely predict the deci- sion (their role as predictors), or do both. They find that both positive and negative reviews are correlated with weekly box office revenue over an eight-week period, suggesting that critics play a dual role: They can influence and predict box office revenue. However, the authors find the impact of negative reviews (but not positive reviews) to diminish over time, a pattern that is more consistent with critics' role as influencers. The authors then compare the positive impact of good reviews with the negative impact of bad reviews to find that film reviews evidence a negativity bias; that is, negative reviews hurt performance more than positive reviews help performance, but only during the first week of a film's run. Finally, the authors examine two key moderators of critical reviews, stars and budgets, and find that popular stars and big budgets enhance box office revenue for films that receive more neg- ative critical reviews than positive critical reviews but do little for films that receive more positive reviews than neg- ative reviews. Taken together, the findings not only replicate and extend prior research on critical reviews and box office performance but also offer insight into how film studios can strategically manage the review process to enhance box office revenue.
Article
Full-text available
We are in the midst of a technological revolution whereby, for the first time, researchers can link daily word use to a broad array of real-world behaviors. This article reviews several computerized text analysis methods and describes how Linguistic Inquiry and Word Count (LIWC) was created and validated. LIWC is a transparent text analysis program that counts words in psychologically meaningful categories. Empirical results using LIWC demonstrate its ability to detect meaning in a wide variety of experimental settings, including to show attentional focus, emotionality, social relationships, thinking styles, and individual differences.
Article
Full-text available
Many consumers consult online reviews before making (online) travel arrangements. Yet, little is known about the impact of these reviews on consumer decision making. This research applies consideration set theory to model the impact of online hotel reviews on consumer choice. An experimental study (N = 168) that includes review valence (positive vs. negative reviews), hotel familiarity (well-known vs. lesser-known hotels), and reviewer expertise (expert vs. non-expert reviewers) as independent factors shows that on average, exposure to online reviews enhances hotel consideration in consumers. This is because positive as well as negative reviews increase consumer awareness of hotels, whereas positive reviews, in addition, improve attitudes toward hotels. These effects are stronger for lesser-known hotels. Reviewer expertise has only a minor – positive – influence on review impact.
Conference Paper
Full-text available
Building on the interpersonal evaluation theory in social psychology, this study explores the existence of a negativity bias in evaluating the helpfulness of online reviews, i.e., whether users perceive a negative review to be more helpful than a positive review. An analysis of 7659 book reviews from Amazon.co.uk shows that a negativity bias disappears after controlling for moderating factors related to evaluation quality such as readability and length. The finding demonstrates that the negativity bias suggested by the social psychology literature is not readily applicable to consumer-generated online reviews. The study contributes to the theorization of word-of-mouth by exploring the qualitative characteristics of consumer-generated reviews in addition to their valence. The study also makes a theoretical contribution to information systems research by introducing and extending the interpersonal evaluation theory to online review research.
Conference Paper
Full-text available
Consumer-generated content (CGC) is growing in importance. Especially online travel reviews written by consumers are ever more available and used to inform travel-related decisions. A Web-based survey of users of the most prominent travel review site, TripAdvisor, was conducted to investigate how other travellers’ reviews inform the trip planning process. Since current CGC statistics show generational and gender differences, the study also aimed at examining whether those carry over into the realm of travel review use. The results show that reviews are used mostly to inform accommodation decisions and are currently not used much for en route travel planning. Gender differences were found for perceived impacts of reviews, with females reaping greater benefits from using reviews, especially in terms of enjoyment and idea generation. Age differences occurred across a variety of perceptions and use behaviours. Implications for travel marketing and travel information systems design are provided.
Conference Paper
Full-text available
As online reviews increasingly become part of the purchasing process, it is important to understand which components of these reviews consumers consider most helpful in facilitating the purchase decision process. Online retailer and rating websites with more helpful reviews offer greater potential value to their consumers. Through two studies, we seek to identify and better understand what makes a helpful consumer review. After an open-ended analysis of the qualities of a review identified by subjects' as helpful, we conducted a controlled experiment that manipulated both the review content and the description of the reviewer. One key finding is that reviews written by a self-described expert are more helpful than those that are not. This information can provide guidance to online retailers and rating websites in their efforts to provide value to their customers.
Article
Full-text available
Customer reviews are increasingly available online for a wide range of products and services. They supplement other information provided by electronic storefronts such as product descriptions, reviews from experts, and personalized advice generated by automated recommendation systems. While researchers have demonstrated the benefits of the presence of customer reviews to an online retailer, a largely uninvestigated issue is what makes customer reviews helpful to a consumer in the process of making a purchase decision. Drawing on the paradigm of search and experience goods from information economics, we develop and test a model of customer review helpfulness. An analysis of 1,587 reviews from Amazon.com across six products indicated that review extremity, review depth, and product type affect the perceived helpfulness of the review. Product type moderates the effect of review extremity on the helpfulness of the review. For experience goods, reviews with extreme ratings are less helpful than reviews with moderate ratings. For both product types, review depth has a positive effect on the helpfulness of the review, but the product type moderates the effect of review depth on the helpfulness of the review. Review depth has a greater positive effect on the helpfulness of the review for search goods than for experience goods. We discuss the implications of our findings for both theory and practice.
Article
Full-text available
This study examines the persuasive effect and awareness effect of online user reviews on movies' daily box office performance. In contrast to earlier studies that take online user reviews as an exogenous factor, we consider reviews both influencing and influenced by movie sales. The consideration of the endogenous nature of online user reviews significantly changes the analysis. Our result shows that the rating of online user reviews has no significant impact on movies' box office revenues after accounting for the endogeneity, indicating that online user reviews have little persuasive effect on consumer purchase decisions. Nevertheless, we find that box office sales are significantly influenced by the volume of online posting, suggesting the importance of awareness effect. The finding of awareness effect for online user reviews is surprising as online reviews under the analysis are posted to the same website and are not expected to increase product awareness. We attribute the effect to online user reviews as an indicator of the intensity of underlying word-of-mouth that plays a dominant role in driving box office revenues.
Article
Full-text available
Online product reviews may be subject to self-selection biases that impact consumer purchase behavior, online ratings’ time series, and consumer surplus. This occurs if early buyers hold different preferences than do later consumers about the quality of a given product. Readers of early product reviews may not successfully correct for these preference differences when interpreting ratings and making purchases. In this study, we develop a model that examines how idiosyncratic preferences of early buyers can affect long-term consumer purchase behavior as well as the social welfare created by review systems. Our model provides an explanation for the structure of product ratings over time, which we empirically test using online book reviews posted on Amazon.com. Our analysis suggests that firms could benefit from altering their marketing strategies such as pricing, advertising, or product design to encourage consumers likely to yield positive reports to self-select into the market early and generate positive word-of-mouth for new products. On the other hand, self-selection bias, if not corrected, decreases consumer surplus.
Article
Full-text available
With the rapid growth of the Internet, the ability of users to create and publish content has created active electronic communities that provide a wealth of product information. However, the high volume of reviews that are typically published for a single product makes harder for individuals as well as manufacturers to locate the best reviews and understand the true underlying quality of a product. In this paper, we re-examine the impact of reviews on economic outcomes like product sales and see how different factors affect social outcomes such as their perceived usefulness. Our approach explores multiple aspects of review text, such as subjectivity levels, various measures of readability and extent of spelling errors to identify important text-based features. In addition, we also examine multiple reviewer-level features such as average usefulness of past reviews and the self-disclosed identity measures of reviewers that are displayed next to a review. Our econometric analysis reveals that the extent of subjectivity, informativeness, readability, and linguistic correctness in reviews matters in influencing sales and perceived usefulness. Reviews that have a mixture of objective, and highly subjective sentences are negatively associated with product sales, compared to reviews that tend to include only subjective or only objective information. However, such reviews are rated more informative (or helpful) by other users. Further, reviews that rate products negatively can be associated with increased product sales when the review text is informative and detailed.By using Random Forest based classiers, we show that we can accurately predict the impact of reviews on sales and their perceived usefulness. We examine the relative importance of the three broad feature categories: 'reviewer-related' features, 'review subjectivity' features, and 'review readability' features, and find that using any of the three feature sets results in a statistically equivalent performance as in the case of using all available features. This paper is the first study that integrates econometric, text mining, and predictive modeling techniques toward a more complete analysis of the information captured by user-generated online reviews in order to estimate their helpfulness and economic impact.
Article
Full-text available
This article explores the implications that dispositional optimism holds for physical well-being. Research is reviewed that links optimism to a number of different positive health-relevant outcomes, ranging from the development of physical symptoms to recovery from coronary artery bypass surgery. Additional findings are described which suggest that these beneficial effects are partly due to differences between optimists and pessimists in the strategies that they use to cope with stress. A number of other potential mediators are also discussed, including some that are physiologic in nature. The article closes with a discussion of the relationships between our own theoretical account of the effects of optimism and several other conceptual approaches.
Conference Paper
Online reviews provide a valuable resource for potential customers to make purchase decisions. However, the sheer volume of available reviews as well as the large variations in the review quality present a big impediment to the effective use of the reviews, as the most helpful reviews may be buried in the large amount of low quality reviews. The goal of this paper is to develop models and algorithms for predicting the helpfulness of reviews, which provides the basis for discovering the most helpful reviews for given products. We first show that the helpfulness of a review depends on three important factors: the reviewerpsilas expertise, the writing style of the review, and the timeliness of the review. Based on the analysis of those factors, we present a nonlinear regression model for helpfulness prediction. Our empirical study on the IMDB movie reviews dataset demonstrates that the proposed approach is highly effective.
Article
This paper explores effects of the emotions embedded in a seller review on its perceived helpfulness to readers. Drawing on frameworks in the emotion and cognitive processing literatures, we propose that over and above a well-known negativity bias, the impact of discrete emotions in a review will vary, and that one source of this variance is reader perceptions of reviewers’ cognitive effort. We focus on the roles of two distinct, negative emotions common to seller reviews: anxiety and anger. In Studies 1 and 2, experimental methods were utilized to identify and explain the differential impact of anxiety and anger in terms of perceived reviewer effort. In Study 3, seller reviews from Yahoo! Shopping websites were collected to examine the relationship between emotional review content and helpfulness ratings. Our findings demonstrate the importance of examining discrete emotions in online word-of-mouth, and they carry important practical implications for consumers and online retailers.
Article
Assessing the quality of user generated con- tent is an important problem of Web 2.0. Currently, most web sites need their users to rate content manually, which is labour intensive and thus happens rarely. The au- tomatic systems in the literature are limited to one kind or domain of discourse. We propose a system to assess the quality of user generated discourse automatically. Our system learns from human ratings by ap- plying SVM classification based on features such as Surface, Lexical, Syntactic, Forum specific and Similarity features. Our system has also shown to be adapt- able to dierent domains of discourse in our experiments on three dierent web fo- rum data sets. The system outperformed the majority class baseline for all three data sets. Our best performing system configu- ration achieves an accuracy of 89.1%, which is significantly higher than the baseline of 61.82%.
Article
This article is Robert Gunning's own assessment of the achieve ments of the Fog Index after twenty years of use. Those in terested in readability formulas will be happy to learn a little more not only about the history and development of the Fog Index but about the applica tions that have been made of it in business and industry, and also in newspaper and govern ment work. Mr. Gunning is well aware, of course, of some of the weaknesses of the index, but obviously he also has rea son to be proud of its achieve ments.
Article
An important area of information systems (IS) research has been the identification of the individual-level beliefs that enable technology acceptance such as the usefulness, reliability, and flexibility of a system. This study posits the existence of additional beliefs that inhibit usage intentions and thus foster technology rejection rather than acceptance. We theorize that these inhibitors are more than just the antipoles of enablers (e.g., the opposite of usefulness or reliability) and so are distinct constructs worthy of their own investigation. Inhibitors are proposed to have effects on usage intentions beyond that of enablers as well as effects on enablers themselves. We report on a series of empirical studies designed to test the existence and effects of inhibitors. A candidate set of six inhibitors is shown to be distinct from enablers. These inhibitors are subsequently tested in a field study of 387 individuals nested within 32 different websites. Effects at both individual and website unit levels of analysis are tested using multilevel modeling. We find that inhibitors have negative effects on usage intentions, as well as on enablers, and these effects vary contingent upon individual or website unit levels of analysis. The overall results support the existence and importance of inhibitors in explaining individual intent to use—or not use—technology.
Article
Drawing from cognitive response models of persuasion, functional emotion theories, and theoretical and empirical work on the influence of message-relevant and message-irrelevant affect on attitudes, this paper presents a model of persuasion that suggests that discrete, message-induced negative emotions influence attitudes through a complex process that centers around the notions of motivated attention and motivated processing. Emotion type, expectation of the message containing reassuring information, argument strength, presence of peripheral cues, emotional intensity, and emotion placement within a message are expected to mediate information processing depth, message acceptance or rejection, and information recall. This model attempts to bridge the gap between the “emotional” and “rational” approaches to persuasion, and it extends current theorizing in the area of emotion and attitude change by (a) linking the concepts of motivated attention and motivated processing to that of expectation of message reassurance, and (b) considering the persuasive effects of negative emotions other than fear, like anger, disgust, sadness, and guilt.
Article
Crowd-funded markets have recently emerged as a novel source of capital for entrepreneurs. As the economic potential of these markets is now being realized, they are beginning to go mainstream, a trend reflected by the explicit attention crowdfunding has received in the American Jobs Act as a potential avenue for economic growth, as well as the recent focus that regulators such as the U.S. Securities and Exchange Commission have placed upon it. Although the formulation of regulation and policy surrounding crowd-funded markets is becoming increasingly important, the behavior of crowdfunders, an important aspect that must be considered in this formulation effort, is not yet well understood. A key factor that can influence the behavior of crowd funders is information on prior contribution behavior, including the amount and timing of others’ contributions, which is published for general consumption. With that in mind, in this study, we empirically examine social influence in a crowd-funded marketplace for online journalism projects, employing a unique data set that incorporates contribution events and Web traffic statistics for approximately 100 story pitches. This data set allows us to examine both the antecedents and consequences of the contribution process. First, noting that digital journalism is a form of public good, we evaluate the applicability of two competing classes of economic models that explain private contribution toward public goods in the presence of social information: substitution models and reinforcement models. We also propose a new measure that captures both the amount and the timing of others’ contribution behavior: contribution frequency (dollars per unit time). We find evidence in support of a substitution model, which suggests a partial crowding-out effect, where contributors may experience a decrease in their marginal utility from making a contribution as it becomes less important to the recipient. Further, we find that the duration of funding and, more importantly, the degree of exposure that a pitch receives over the course of the funding process, are positively associated with readership upon the story’s publication. This appears to validate the widely held belief that a key benefit of the crowdfunding model is the potential it offers for awareness and attention-building around causes and ventures. This last aspect is a major contribution of the study, as it demonstrates a clear linkage between marketing effort and the success of crowd-funded projects.
Article
User-Generated Content (UGC) on social media platforms and product search engines is changing the way consumers shop for goods online. However, current product search engines fail to effectively leverage information created across diverse social media platforms. Moreover, current ranking algorithms in these product search engines tend to induce consumers to focus on one single product characteristic dimension (e.g., price, star rating). This approach largely ignores consumers ’ multi-dimensional preferences for products. In this paper, we propose to generate a ranking system that recommends products that provide on average the best value for the consumer’s money. The key idea is that products that provide a higher surplus should be ranked higher on the screen in response to consumer queries. We use a unique dataset of U.S. hotel reservations made over a three-month period through Travelocity, which we supplement with data from various social media sources using techniques from text mining, image classification, social geotagging, human annotations, and geo-mapping. We propose a random coefficient hybrid structural model, taking into consideration the two sources of consumer heterogeneity the different travel occasions and different hotel characteristics introduce. Based on the estimates from the model, we infer the economic impact of various location and service characteristics of hotels. We then propose a new hotel ranking
Conference Paper
Combining econometric analysis with text mining techniques, this study attempts to explore why some online product reviews have no usefulness rating through examining review posting time and text features. Later posting time may reduce the probability of some online reviews being seen and thus lead to their being not rated for usefulness. Besides, the neutral diagnosticity of reviews reflected from the text features may cause difficulty for readers to judge and evaluate the usefulness of these reviews. Our study finds that, though not being seen due to later posting time obviously explains no usefulness rating for some online reviews, the neutral diagnosticity of these reviews is also an important and non-neglectable cause for their lack of usefulness rating. Further, we identify the text features which may lead to the neutral diagnosticity of the review. Our study has implications for online product reviews website managers in identifying and dismissing the reviews with no usefulness rating to improve readers' information retrieving efficiency and also for reviewers in improving the quality of their reviews.
Conference Paper
User-supplied reviews are widely and increasingly used to enhance e- commerce and other websites. Because reviews can be numerous and varying in quality, it is important to assess how helpful each review is. While review helpfulness is currently assessed manu- ally, in this paper we consider the task of automatically assessing it. Experi- ments using SVM regression on a vari- ety of features over Amazon.com product reviews show promising results, with rank correlations of up to 0.66. We found that the most useful features in- clude the length of the review, its uni- grams, and its product rating.
Article
Consumer-generated product reviews have proliferated online, driven by the notion that consumers' decision to purchase or not purchase a product is based on the positive or negative information about that product they obtain from fellow consumers. Using research on information processing (Chaiken 1980) as a foundation, we suggest that in the context of an online community, reviewer disclosure of identity-descriptive information is used by consumers to supplement or replace product information when making purchase decisions and evaluating the helpfulness of online reviews. Using a unique dataset based on both chronologically compiled ratings as well as reviewer characteristics for a given set of products and geographical location-based purchasing behavior from Amazon, we provide evidence that community norms are an antecedent to reviewer disclosure of identity-descriptive information. Amazon members rate reviews containing identity-descriptive information more positively, and the prevalence of reviewer disclosure of identity information is associated with increases in subsequent online product sales. In addition, we show that when reviewers are from a particular geographic location, subsequent product sales are higher in that region, thus highlighting the important role of geography in electronic commerce. Taken together, our results suggest that identity-relevant information about reviewers shapes community members' judgment of products and reviews. Implications for research on the relationship between online reviews and sales, peer recognition systems, and conformity to online community norms are discussed.
Article
One of the problems in public education and mass communication is how to tell whether a particular piece of writing is likely to be readable to a particular group of readers. Two major solutions are possible: measuring and predicting readability. Measuring, by judgments or tests, involves using readers. Predicting by readability formulas, does not involve readers but instead uses counts of language elements in the piece of writing. This article reviews formulas and related predictive devices since 1960. Four categories are presented: 1) recalculations and revisions of existing formulas; 2) new formulas, for general purpose or special purpose use; 3) application aids, for both manual and machine use; and, 4) predictions of readability for foreign languages. It concludes with suggestions for choosing a formula, based upon the following considerations: 1) special versus general needs, 2) manual versus machine application, 3) simple versus complex formulas, 4) word length versus word list formulas; and, 5) sentence length versus sentence complexity. Finally, the article stresses that formulas provide good indices of difficulty