Figure 1 - uploaded by Edward C Malthouse
Content may be subject to copyright.
Source publication
We study the effect of the volume of consumer reviews on the purchase likelihood (conversion rate) of users browsing a product page. We propose using the exponential learning curve model to study how conversion rates change with the number of reviews. We call the difference in conversion rate between having no reviews and an infinite number \textit...
Context in source publication
Context 1
... over the bulk of that effect happens within the first 10 reviews the product receives. Figure 1 displays the fitted curve. Note that this effect is isolated for when the display of reviews happened, i.e., when disp equals 1 in Equation 1. Figure 2 compares the value of reviews for high-and low- priced items. ...
Citations
... Online reviews provided by customers are one part of a series of purchases made by many customers. Currently, online reviews can be found on various websites, such as Yelp, Facebook, Google, IMDb, and many more (Askalidis & Malthouse, 2016). Reviews given by customers can be used as a source for obtaining various information (Trenz & Berger, 2013). ...
The growth in the retail industry means that the retail industry must have a competitive advantage to compete. One source of competitive advantage is customer experience. One factor that has a positive influence on customer experience is the service provided by frontline employees. Nowadays, customers can easily share their experiences and information in online reviews. Therefore, a good understanding of online reviews is necessary to maintain customer satisfaction. This paper proposes a new method for obtaining information from online reviews available on online review platforms such as Google Maps. Reviews on the website will be scraped and translated into English using the large language model (LLM). The translated reviews will be translated to obtain aspects, sentiments, and opinions using an aspect-based sentiment analysis (ABSA) model that has been previously drilled using a dataset in English. The findings are visualized into Pareto diagrams and word cloud to identify aspects related to human resources that most influence the negative or positive ratings given by customers through online reviews.
... 1 Introduction E-commerce platforms frequently allow customers to provide feedback (reviews) on the products or services they have purchased. Customer reviews are critical mechanisms for reinforcing product and service quality, increasing consumer satisfaction and purchase intent, and identifying areas for business improvement (Geng and Chen, 2021;Askalidis and Malthouse, 2016). Figure 1 illustrates an example product review from a major online marketplace in Brazil 1 . ...
Product reviews are valuable resources that assist shoppers in making informed transactions by reducing uncertainty within the purchase process. However, user-generated content is not always secure or adequate. The goal of customer review moderation is to ensure both a secure environment for all parties participating and the integrity of the review information. Content moderation is a difficult task even for human moderators, and in some circumstances, due to the enormous volume of reviews, manual content moderation is not practical. In this paper , we present the experiments carried out using automated machine learning (AutoML) for moderating product reviews on one of Brazil's largest e-commerce platforms. Our machine learning-based solution is faster and more accurate than the previously used content moderation system, performed by a third-party company system dependent on human intervention. Overall, the results showed that our model was 31.12% more accurate than the third-party company system and it had a fast development due to the use of AutoML techniques.
... The investigation employed speci c keywords, including gels, strips, light-activating products, and teeth whitening, on an e-commerce platform. Information was meticulously collected and cataloged, encompassing particulars such as product name/brand, manufacturer, formulation, indications, pricing, and supplementary data such as customer ratings and reviews [7].The search was performed on November 2, 2023. ...
Objectives: This study aimed to compile and evaluate over-the-counter (OTC) toothwhitening products from a prominent e-marketplace, assessing their bleaching effectiveness and impact on enamel.
Methodology: Thirty-eight intact tooth sections were randomly divided into three groups: Group I, the positive control, was treated with a dentist-prescribed bleaching agent (DPA) (Opalescence, Ultradent, USA); Groups II and III were treated with the lowest-rated (LRA) and highest-rated (HRA) e-market bleaching agents, respectively. Ten samples per group were subjected to spectrophotometric analysis for bleaching efficacy, ten for postbleaching microhardness, and two per group for morphological evaluation through scanning electron microscopy (SEM). Statistical analyses included one-way ANOVA, post hoc tests, and Student’s t tests, maintaining a significance level of P <0.05.
Results: The e-commerce search revealed 15 e-market products out of which most of them lacked usage instructions and comprehensive composition information. DPA exhibited superior tooth whitening, in contrast with the poorly rated online agent, which showed asignificantly lower degree of color change (P=0.007). Microhardness was significantly lower in the LRA treatment group (14.2%) than in the control and HRA treatment groups (8.84% and 7.26%, respectively) (P >0.05). Furthermore, LRA caused severe topographical alterations to the enamel.
Conclusion: e-portal OTC teeth whitening products lackvital information, while dentist-prescribed products outperform LRA products in terms of efficacy and enamel preservation.
Clinical relevance: Patients’ inclination toward easily accessible online products, particularly from platforms such asAmazon, may result in overuse and consequential deleterious effects on dental tissues.
... Nearly 95% of customers read online reviews before making a purchase (Spielger Research Center 2017). Customer reviews can significantly influence customer perception (Park et al. 2007, Askalidis andMalthouse 2016). However, very little is known about the supply-side impacts of online reviews. ...
Problem definition: Customer reviews are essential to online marketplaces. However, reviews typically vary; ratings of a product or service are rarely the same. In many service marketplaces, including the ones for solar panel installations, supply-side participants are active. That is, a seller must make a proposal to serve each customer. In such marketplaces, it is not clear how (or if) the dispersion in customer reviews affects the seller activity level and number of matches in the marketplace. Our paper examines this by considering both ratings and text reviews. To our knowledge, this is the first paper that empirically studies how the review dispersion affects a seller’s activity level and the number of matches in an online marketplace with active sellers. Distinct from literature, we examine the relationship between the review dispersion and supply-side activities in an online service marketplace. Methodology/results: We collaborated with one of the largest online solar marketplaces in the United States that connects potential solar panel adopters with installers. We obtained a unique data set from the marketplace for 2013 − 2018. We complement this with public data sets. Our analysis uses traditional econometrics methods, a clustering method, and the deep-learning-based natural-language-processing model BERT developed by Google AI. We find that the dispersion in customer reviews has a significant and inverted U-shaped relationship with an installer’s marketplace activity level. Intuitively, a marketplace operator would favor having more sellers with perfect ratings. In contrast, we identify a significant and inverted U-shaped relationship between the market-level review dispersion and transactions. Managerial implications: Our paper provides key insights to marketplace operators and sellers. We find that in contrast to general belief, an operator can improve its market transactions by keeping/promoting sellers with low ratings or avoiding (negative) review filtering. Furthermore, sellers’ implementation of “rating gating” to avoid negative reviews may backfire for them by reducing their matches.
Supplemental Material: The e-companion is available at https://doi.org/10.1287/msom.2021.0104 .
... Price is considered as an important stimulus to attract users and help them take into account upon making online purchases [38]. In the study of Askalidis and Edward [39], they discovered that expensive goods have a larger value for reviews than cheaper goods. Compared to 190% for low priced items, high priced ones can see a conversion rate increase of up to 380% as they gain reviews. ...
Using signaling theory, this study unpacked the mechanisms through which online review information quality and reviewer information credibility influence online review helpfulness, in e-commerce context. Conducting a survey with users in Danang having read online reviews on Shopee.vn, 244 valid responses were used to evaluate the research model via PLS-SEM software. The study found that the information quality of online reviews strongly influences the helpfulness of online reviews compared to the information credibility of previous reviewers. Additionally, priced goods have a moderating effect on the relationship between online information credibility and online reviews helpfulness; and that relationship will be significant in high-priced products. This study makes a theoretical contribution to online reviews by elucidating the mechanisms of impact of review/reviewer information on reviews helpfulness and the moderating effect of product prices.
... Askalidis and Malthouse studied the impact of reviews on the purchase of other hesitating customers. They have found that customers will treat these reviews very importantly and see them as a signal [1]. The volume of reviews can have positive effects by increasingdhbgrb the product's credibility and demonstrating its popularity. ...
The rapid development of online shopping sites has pushed people's shopping to a new way. Online shopping not only provides convenience to people but also "suggestions." Moreover, there are always many reviews from previous consumers on shopping websites, helping people know more about the product and make decisions. This paper represents the sentiment analysis of Amazon reviews using three models: Random Forest, Naive Bayes, and SVM. These models are trained with token counts, and term frequency-inverse document frequency (TF-IDF) features to make better comparisons. Classification performances are evaluated by precision, recall, and F-1 scores, and exploration is implemented into the dataset providing information about Amazon reviews. The results show that Random Forest and SVM models perform well on positive-labeled data but provide suboptimal results on negative-labeled and neutral-labeled data. Overall, Naive Bayes has the best performance for all three classifications. However, classifications might be biased during the analysis. Thus, more improvements are expected in future research about this topic to obtain more accurate and ideal results, and more machine learning models are supposed to be implemented.
... Các nghiên cứu cho thấy rằng phần lớn người tiêu dùng tin tưởng đánh giá trực tuyến hơn so với các nguồn thông tin về sản phẩm, dịch vụ khác và dường như họ cũng tin tưởng các sản phẩm có nhiều đánh giá hơn những sản phẩm không có đánh giá. (Askalidis & Malthouse, 2016) đã chứng minh bằng thực nghiệm rằng đánh giá trực tuyến có khả năng tác động đến ý định mua hàng cao hơn 27%. Bằng cách hiểu rõ hơn tác động của các bài đánh giá do người tiêu dùng trực tuyến tạo ra, các thương hiệu có thể nâng cao trải nghiệm mua sắm tổng thể cho người dùng của họ bằng cách đặt các bài đánh giá nổi bật trên các trang sản phẩm của họ . ...
Internet đã cung cấp cho người tiêu dùng phương tiện dễ dàng để có được thông tin sản phẩm từ những người tiêu dùng khác và cũng để chia sẻ kinh nghiệm tiêu dùng sản phẩm của chính họ. Hoạt động của người tiêu dùng đánh giá và xếp hạng sản phẩm trực tuyến, sau đó lan tỏa những nhận định hoặc đánh giá này tới những người tiêu dùng khác được gọi là đánh giá trực tuyến (Chatterjee, 2001). Trong bối cảnh TMĐT nói chung và bán lẻ trực tuyến nói riêng đang có sự phát triển mạnh mẽ, các bài đánh giá trực tuyến cung cấp cho người tiêu dùng trực tuyến những thông tin bổ sung về thương hiệu và sản phẩm, đồng thời thúc đẩy họ tiến tới quyết định lựa chọn mua hoặc không. Trên cơ sở tổng quan các nghiên cứu có liên quan, bài viết đã đề xuất mô hình nghiên cứu ảnh hưởng của nguồn thông tin đánh giá trực tuyến tới quyết định mua trực tuyến của người tiêu dùng tại Việt Nam. Kết quả nghiên cứu đã cho thấy, chất lượng nguồn thông tin đánh giá trực tuyến có tác động đáng kể tới quyết định mua hàng của người tiêu dùng trực tuyến. Thông qua kết quả nghiên cứu, tác giả cũng đưa ra một số thảo luận để làm rõ đặc trưng trong tiêu dùng trực tuyến của người tiêu dùng Việt Nam, đồng thời xác định một số hạn chế trong nghiên cứu và các hướng phát triển của nghiên cứu trong thời gian tới.
... (Askalidis & Malthouse, 2017). Informasi dapat bersifat positif maupun negatif (Sianipar & Yoestini, 2021).Dari beberapa pendapat yang telah disampaikan di atas, customer review menurut penelitian ini menjelaskan bahwa Online Customer Review merupakan ulasan pelanggan online dalam memberikan informasi baik/buruk tentang produk dan rekomendasi dari perspektif konsumen yang menjadi penting bagi konsumen lain sebelum melakukan pembelian secara online. ...
This research seeks to explain the moderating effect of product quality on the relationship between online customer reviews and ratings and online purchasing decisions. Unknown number of Tokopedia application users in Jakarta constitute the population for this research. This study used a technique of purposive sampling in which the sample must meet the requirements specified. For data collection, online questionnaires were used in this study. Smart PLS3 software is used for data processing. As a result, 100 Tokopedia application users fulfilled the research criteria and participated in this study. The findings of the research indicate that product quality moderates the impact of online customer reviews on online purchase decisions. Similarly, product quality moderates the impact of online customer ratings on purchase choices made online. The results of this research may give entrepreneurs with information on the online behavior of customers.
... Within these reviews, customers share their opinion on and evaluation of a product or service online, which potential customers can refer to when informing themselves about this specific product or service. Online customer reviews have become an important element for most online ecommerce platforms (Trenz & Berger, 2013), which many people rely on when searching for information and making purchasing decisions (Askalidis & Malthouse, 2016). In recent years, online customer reviews have been used as a data source in research to investigate, for example, customers' or users' assessment of hotels (Berezina et al., 2016), physicians (Kordzadeh, 2019), airlines (Lucini et al., 2020) or public libraries (Borrego & Comalat Navarra, 2021). ...
This cumulative doctoral thesis examines the role of mobile devices in young children's information behavior from different perspectives. On the one hand, it explores whether information-related activities are part of young children's use of mobile technologies. On the other hand, it investigates whether aspects of children's information behavior play a role in parents' and children's perceptions of mobile device use. The first study presented in this thesis gains exploratory insight into young children's use of mobile devices through interviews with parents of families with children aged one to six years. Based on a secondary analysis of the interview data, the second study examines how parents perceive and mediate young children's use of mobile devices and discusses how this might influence children's information behavior. By applying a uses and gratifications approach, the third study investigates what customer reviews for a tablet for children reveal about the use of this device and expectations of the families. Using a multi-method approach, the fourth study places a particular focus on the inclusion of children's perspectives and investigates how children aged four to six years use mobile devices and whether aspects related to children's information behavior play a role in families' perceptions of this use. Overall, the results show that mobile devices can clearly play a role in young children's information behavior, although their potential for children's information discovery is not always prominent in parents' and children's perceptions. With these findings, this work makes an important contribution to addressing existing research gaps regarding young children's information behavior in general as well as in the specific context of mobile device use.
... Older studies have also shown the relevance of customer reviews in purchase decisions (Gu et al., 2012;X. Li & Hitt, 2010), including that reviews are the most relevant factor after price (Askalidis & Malthouse, 2016). As such, online product reviews affect product reputations (Filieri et al., 2015), sales volumes (He et al., 2020), and merchants' profits (Dellarocas, 2006). ...
... As such, online product reviews affect product reputations (Filieri et al., 2015), sales volumes (He et al., 2020), and merchants' profits (Dellarocas, 2006). In fact, the conversion rate of a product can increase by as much as 270% if it accumulates even a small number of reviews that users can access (Askalidis & Malthouse, 2016). ...
Along with the ever-increasing portfolio of products online, the incentive for market participants to write fake reviews to gain a competitive edge has increased as well. This article demonstrates the effectiveness of using different combinations of spam detection features to detect fake reviews other than the review-based features typically used. Using a spectrum of feature sets offers greater accuracy in identifying fake reviews than using review-based features only, and using a machine learning algorithm for classification and different amounts of feature sets further elucidates the difference in performance. Results compared by benchmarking show that applying a technique prioritizing feature importance benefits from prioritizing features from multiple feature sets and that creating feature sets based on reviews, reviewers and product data can achieve the greatest accuracy.
