No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
Online review analysis-based multi-criteria decision-making for evaluating patient satisfaction: A case study of the Haodf website
Purpose
This study aims to investigate the impact of physician efforts in online reviews on outpatient appointments, while also examining the moderating effect of physician title.
Design/methodology/approach
This study employs the heuristic-systematic model (HSM) to analyze the impact of physician efforts on outpatient appointments. Subsequently, a fixed effect model is employed to examine the research model using an 89-week panel dataset (from April 16, 2018 to December 29, 2019) comprising appointment and online review information pertaining to 8,157 physicians from a prominent online health community in China.
Findings
The findings suggest that physicians with lower professional titles exhibit a significantly higher inclination to enhance heuristic information (e.g. attracting helpful votes) compared to those with higher professional title. All physicians can enhance their outpatient appointments by dedicating efforts towards improving systematic review information, but physician title would weaken the relationship. Moreover, the effect of increasing review volume is considerably more substantial than that of increasing review length, which also surpasses the influence of providing managerial response.
Originality/value
Unlike previous studies that primarily focus on patients’ perspectives, this paper represents one of the pioneering effects to examine physicians’ engagement in online reviews.
It is very common to use linguistic information to solve decision-making problems in real life, and the double hierarchy hesitant fuzzy linguistic term set (DHHFLTS) has been widely used because of its powerful ability of expressing complex linguistic information. There is no doubt that the comparison method of double hierarchy hesitant fuzzy linguistic elements (DHHFLEs) not only occupies an important theoretical and practical position, but also is the basis for further study of DHHFLTSs. However, the existing comparison methods of DHHFLEs still have some limitations. Therefore, this paper proposes a new DHHFLE comparison method, which is an improvement and perfection of the existing DHHFLE comparison methods. In addition, considering that the current research on distance and similarity measures of DHHFLEs is mostly based on the algebraic point of view, this paper proposes a cosine similarity measure of DHHFLEs, which fills the gap in the study of distance and similarity measures from the geometric point of view. Then, the cosine similarity-based DHHFL-ELECTRE II method is proposed to solve the multi-attribute decision-making (MADM) problem in the double hierarchy hesitant fuzzy linguistic environment. Finally, this method is used to solve a MADM problem in the performance evaluation of financial logistics enterprises. The results show that the proposed method has certain applicability and feasibility.
Sentiment classification can provide the decision support of social applications such as trend judgment, public opinion monitoring, etc. However, the accuracy of sentiment classification for Chinese Weibo is still not satisfactory due to the complexity of Chinese. In addition, affected by the different organisational structure levels, the sentiment tendency of fewer Weibo Comments may be judged to be the opposite. To solve the problem above, this paper presents a Chinese sentiment classification model based on extended sentiment dictionary and organisational structure of comments. First, the sentiment dictionary can be extended by using seven dictionaries, which include the base sentiment dictionary and six additional dictionaries. Then, the sets of rules are constructed, which include inter-sentence rules and organisational structure rules. Finally, comments on three hot topics are crawled and used to make the data sets for sentiment calculation. Accordingly, based on the result of sentiment calculation, sentiment classification is completed. The effectiveness of the proposed model is verified through comparison experiments, and the experimental results are also discussed.
The research provides a multi-criteria group decision support model for hotel selection according to traveller preference characteristics. Specifically, the study attempts to identify characteristic preferences among travellers through online reviews and then generate recommendation lists under these characteristics. Utilizing a sample of 48,756 online reviews on TripAdvisor.com, the research exploits natural language processing to acquire high-frequency feature words and employs these features to group online reviews for filtering unrelated ones. Subsequently, online reviews and fuzzy theory are combined to develop a decision support model, by utilising the information of user ratings and text comments. In addition, the related extension of the theoretic knowledge is presented. The findings demonstrate that, hotel quality varies under different characteristics and a comprehensive evaluation of hotels would encounter difficulty meeting travellers’ demands, and the proposed model exhibits great performance in addressing this condition. The study can enable travellers to make a satisfactory hotel selection that matches their expectation to a high degree and also provides implications for hoteliers to understand tourist preferences and for tourism websites to optimize management strategies.
With the excessive consumption and pollution of water resources, the sustainable development of water resources poses a serious threat currently. How to perceive and prevent the degradation of water resource in advance is an urgent problem. The water resource carrying capacity (WRCC) is a significant indicator to reflect the condition of water resources in a region. Resounding to these circumstances, our research establishes a decision support framework to solve WRCC risk evaluation issues. First, hesitant probabilistic fuzzy sets (HPFSs) are selected as a representation for the evaluation information in the expert group. Aimed at existing studies of HPFSs, some limitations are overcome involving the distance and comparison rule. Secondly, a TODIM‐PROMETHEE II based multi‐criteria group decision making (MCGDM) method is developed to overcome the inherent restrictions of PROMETHEE II method and make it suitable for a practical decision‐making condition with bounded rationality. Subsequently, a case study is utilized to demonstrate the feasibility of our newly proposed decision support framework, followed by a sensitivity analysis and a comparison analysis. The outcome indicates that the framework has an excellent performance to solve this kind of MCGDM issues.
Decision making models are constrained by taking the expert evaluations with pre-defined numerical or linguistic terms. We claim that the use of sentiment analysis will allow decision making models to consider expert evaluations in natural language. Accordingly, we propose the Sentiment Analysis based Multi-person Multi-criteria Decision Making (SA-MpMcDM) methodology for smarter decision aid, which builds the expert evaluations from their natural language reviews, and even from their numerical ratings if they are available. The SA-MpMcDM methodology incorporates an end-to-end multi-task deep learning model for aspect based sentiment analysis, named DOC-ABSADeepL model, able to identify the aspect categories mentioned in an expert review, and to distill their opinions and criteria. The individual evaluations are aggregated via the procedure named criteria weighting through the attention of the experts. We evaluate the methodology in a case study of restaurant choice using TripAdvisor reviews, hence we build, manually annotate, and release the TripR-2020 dataset of restaurant reviews. We analyze the SA-MpMcDM methodology in different scenarios using and not using natural language and numerical evaluations. The analysis shows that the combination of both sources of information results in a higher quality preference vector.
Present work proposes novel fuzzy information based TODIM approaches that can deal with the evaluations under complex interval-valued intuitionistic fuzzy (CIVIF) environment. The proposed approaches have been referred to as complex interval-valued intuitionistic fuzzy-TODIM (CIVIF-TODIM) approaches. The proposed method encompasses the characteristic features of a complex intuitionistic fuzzy set, interval-valued fuzzy set, and TODIM methodology. At first, the definitions associated with CIVIF have been discussed and then the methodological steps involved in classical TODIM have been delineated. The classical TODIM approach is then extended to deal with group decision-making problems under the CIVIF environment. Robustness, effectiveness, applicability, and the improvements made to the extant fuzzy TODIM methods by the proposed methodology have been adjudged through the consideration of illustrative examples solved by the past researcher. Sensitivity analysis with respect to the attenuation factor as well as the criteria weights has been provided to justify the robustness of the proposed methods. A comparative analysis with the existing fuzzy-TODIM approaches has been delineated and a comprehensive analysis of the ranking results obtained for different distance measures at each value of attenuation factor is provided towards the end of the work. The carried out inclusive analysis on the approaches that have been proposed in the present work reveals that the proposed CIVIF fuzzy TODIM approaches are superior to the existing fuzzy TODIM methods. Therefore, the present study provides its contribution to the domain of decision-making framework through the approaches that provide for dealing with complex, uncertain, and linguistic information in an efficient manner.
In the multi‐criteria group decision‐making (MCGDM) problems with great uncertainty, making full use of participants' evaluation information could help improve the accuracy and reliability of decision results. Probabilistic linguistic term set (PLTS) is an effective tool to represent qualitative data and can fully express the hesitation and preference of decision makers. Therefore, this paper aims to propose an MCGDM method based on PLTSs. In the proposed method, the projection of PLTSs is explored to measure the distance and angle differences between two objects, and Bayesian best–worst method (Bayesian BWM) is used to determine the aggregated final weights of criteria. Besides, the elimination and choice translating reality III (ELECTRE III) method combined with distillation algorithm deals with the projection of PLTSs to obtain the alternatives' ranking of each decision maker. Then, the weighted convex median voting rule is developed to integrate the rankings results regarding all decision makers, which can solve the conflict of ranking results among experts and ensure that the comprehensive ranking results are reasonable and practical. Finally, a case study of health‐care waste management is designed and comparative analyses are implemented to show the effectiveness and advantages of the proposed method.
Background:
Sarcopenia, defined as the age-associated loss of muscle mass and strength, can be effectively mitigated through resistance-based physical activity. With compliance at ~40% for home-based exercise prescriptions, implementing a remote-sensing system would help patients and clinicians understand treatment progress and increase compliance. Inclusion of end users in the development of mobile applications for remote sensing systems can ensure that they are both user-friendly and facilitate compliance. With advancements in natural-language processing (NLP) there is potential for these methods to be used with data collected through the user-centered design process.
Objective:
The objective of our study was to develop a mobile application for a novel device through a user-centered design process with both older adults and clinicians while exploring if data collected through this process can be used in natural language processing and sentiment analysis methods.
Methods:
Through a user-centered design process, we conducted semi-structured interviews during the development of a geriatric-friendly Bluetooth-connected Resistance Exercise Band App. We interviewed patients and clinicians at weeks 0, 5, and 10 of the development of the app. Each semi-structured interview consisted of heuristic evaluations, cognitive walkthroughs, and observations. We used the Bing sentiment library for sentiment analysis interview transcripts, then applied NLP based Latent Dirichlet Allocation (LDA) topic modeling to identify differences and similarities in patient and clinician participant interviews. Sentiment was defined as the sum of positive and negative words (each word with a +/- 1 value). To assess utility, we used quantitative assessment questionnaires - System Usability Scale (SUS) and Usefulness, Satisfaction & Ease of use (USE). Finally, we used multivariate linear models - adjusting for age, sex, subject group (clinician vs. patient), and development - to explore the association between sentiment analysis and SUS and USE outcomes.
Results:
The mean age of the 22 participants was 68 years old, 17 (77%) of which were female. The overall mean SUS score was 66.4 (SD: 13.6) and mean USE score was 41.3 (SD: 15.2). Both patients and clinicians provided valuable insights into the needs of older adults when designing and building an application. The mean positive-negative sentiment per sentence for patients was 0.19 (SD = 0.21) and 0.47 (SD = 0.21) for clinician interviews. We found a positive association with positive sentiment in an interview and SUS score (β = 1.38 [95%CI = 0.37-2.39], P-value = .01). There was no significant association between sentiment and USE. LDA analysis found no overlap between patients and clinicians in the eight topics identified.
Conclusions:
Involving patients and clinicians allowed us to design and build an application that is user-friendly for older adults while supporting compliance. This is the first analysis using NLP and usability questionnaires in the quantification of the user-centered design of technology for older adults.
Clinicaltrial:
Sentiment analysis of Chinese micro-blog based on sentiment dictionary has become a challenging research subject in the field of artificial intelligence. However, due to insufficient sentiment words, Chinese micro-blog sentiment analysis is difficult to process high accuracy. Aimed at this issue, we propose a method for constructing multiple sentiment dictionaries, which mainly constructs original sentiment dictionary, emoji dictionary, and other related dictionaries. Among them, we have innovatively constructed a Chinese micro-blog new word sentiment dictionary. Multiple sentiment dictionaries increase the coverage of sentiment words. At the same time, we further analyze semantic rule sets between Chinese micro-blog texts and take the inter-sentence analysis rules and sentence pattern analysis rules into the sentiment analysis of Chinese micro-blog, which further improves the accuracy of Chinese mi-cro-blog sentiment analysis. Finally, based on the method of multiple sentiment dictionaries and semantic rule sets, we propose an algorithm for Chinese micro-blog sentiment calculation from complex sentences to clauses and then from clauses to words, and finally combined with the emoji. This algorithm can accurately classify Chinese micro-blog into positive Chinese micro-blog, negative Chinese micro-blog, and neutral Chinese micro-blog. The experimental results show that this method has greatly improved the sentiment analysis of Chinese micro-blog.
Online reviews are playing an increasingly important role in how patients select and evaluate health‐care providers. Physician rating websites not only act as open platforms for patients to share their experiences, but can also offer valuable feedback for physicians to improve the quality of care. In this study, we analyze over one million physician reviews across 17 medical specialties and investigate the relationship between operational efficiency and patient satisfaction. We combine econometrics models with text analytics techniques to quantify the effect using both patients' ratings of physicians and their qualitative review narratives. The results provide strong empirical evidence that operational inefficiency negatively influences patient satisfaction. Specifically, a waiting time longer than 17 min will, on average, reduce the odds of getting a high rating status by 14%. Though many health care ratings examined in this study do not mitigate the negative effects brought on by long waiting time, patient narratives reflecting the importance of technical and interpersonal qualities to patients suggest a more complex set of relationships between waiting time and patient satisfaction. Our study showcases the usefulness of online physician reviews and reveals unique insights for improving the delivery of patient‐centered health care.
Nowadays, water security is becoming increasingly prominent and the water security problem becomes a primary bottleneck restricting China’s future sustainable development. Water security in China is thus worth conducting an in-depth study. This paper aims to explore an effective water security evaluation method. Based on the proposed definition of water security, an evaluation index system of water security is first built from the perspective of “pressure–state–response” conceptual model. Considering the indicators’ uncertainty and the decision makers’ (DMs’) limited knowledge, the DMs usually use linguistic terms to express their judgements. As a new type of linguistic variable, probabilistic linguistic term set (PLTS) not only allows the DMs to express their judgements with multiple linguistic terms but also can reflect the DMs’ different preference degrees over these possible linguistic terms. For the water security issue under probabilistic linguistic environment, a programming model is developed to derive the attribute weights. Then, the TODIM (an acronym in Portuguese for interactive multi-criteria decision making) method, which considers the psychological factors of the DMs, is used to evaluate water security based on the PLTS. Furthermore, a case study is conducted and some discussions and comparative analysis are carried out according to the case results.
The Natural Language Toolkit is a suite of program modules, data sets and tutorials supporting research and teaching in com- putational linguistics and natural language processing. NLTK is written in Python and distributed under the GPL open source license. Over the past year the toolkit has been rewritten, simplifying many linguis- tic data structures and taking advantage of recent enhancements in the Python lan- guage. This paper reports on the simpli- fied toolkit and explains how it is used in teaching NLP.
Online medical platform is a platform for patients to post their medical experience, collect medical information, and link doctors and patients for related medical activities. As the number of patients and doctors registered on the platform increases, there is an urgent need to consider how patients can identify useful information from the vast amount of information to help them make medical choices, and how the platform can provide distinctive medical choices based on the risk preferences of patients. In this paper, we propose a decision-making model that integrates a machine-learning method and a multi-criteria decision-making method to help patients to select physicians based on user-generated content considering interactive criteria and risk preferences of patients. Firstly, by data mining methods, various criteria included in user-generated content that influence patients' selection behavior are retrieved to construct a physician evaluation system. Secondly, a sentiment analysis method based on a medical review corpus is developed to mine satisfaction information from text reviews. Finally, a multi-criteria decision-making method is proposed considering patients' risk-averse preferences for medical services and the interactions among criteria. The validity of the proposed model is demonstrated by a case study of ranking psychologists from haodf.com. The comparisons with other methods and sensitivity analysis results provide suggestions to patients to choose psychologists and the website to rank psychologists.
Energy performance contracting (EPC) mechanism is a good choice for conducting energy-saving renovation projects of public buildings. Furthermore, risk analysis is critical to smoothly implement these EPC projects. Therefore, this paper intends to set up a large-scale group decision-making (LGDM) framework based on delegation mechanism to rank risk factors of EPC projects. Firstly, some risk factors and evaluation criteria are identified. Meanwhile, the assessment is expressed as picture fuzzy numbers (PFNs) to handle conflicting opinions and refusals. Then, a novel bidirectional projection measure that considers both distance and included angle is defined, which can better describe the difference between two PFNs. Next, this paper uses a suitable algorithm to cluster experts and presents a delegation mechanism to allocate trust weights of external experts to internal experts. Then, a new method to protect minority opinions is presented. In addition, we use preference risk coefficient to integrate the uncertainty of decision information in consensus-reaching process (CRP), which reduces the risk of LGDM. We come up with an extended MULTIMOORA method to make full use of three parts of MULTIMOORA method. Moreover, the proposed framework is successfully implemented in a case study and some risk mitigation measures and management implications are presented.
An increasing number of travelers like to share their experience and feelings about hotel stays through social media, generating a sheer volume of online hotel reviews. The user-generated comments contain their preferences for different aspects of hotels, which are helpful for hoteliers to improve hotels’ services. The key of deriving customer preferences from online hotel reviews is to identify fine-grained sentiment towards hotel attributes. However, the existing fine-grained sentiment analysis approaches cannot address the implicit aspect-level terms extraction very well, which is necessary to deal with the common situation that some aspects are omitted in the online reviews. To better understand customer preferences, we propose an unsupervised approach for aspect-level sentiment analysis with the implicit hotel attributes into consideration by integrating word embedding, co-occurrence and dependency parsing. A method based on overall sentiment values of hotel attributes is used to measure the customer preferences to support the hotel services analysis. Finally, online hotel reviews crawled from Ctrip.com are used to verify the proposed approach, and the results show that the hybrid approach outperforms the individual included techniques with respect to the sentiment classification performance. The analysis of customer preference for Dalian Bayshore Hotel suggests that the hotel’s facility should be upgraded urgently, and different types of customers pay different attention to hotel attributes, such as price, hygiene, and location.
Purpose
The purpose of this paper is to show the value of open-ended narrative patient reviews on social media for elucidating aspects of hospital patient satisfaction.
Design/methodology/approach
Mixed methods analyses using qualitative (manual content analyses using grounded theory and algorithmic analyses using the Natural Language Toolkit) followed by quantitative analyses (negative binomial regression).
Findings
Health-care team communication, health-care team action orientation and patient hospital room environment are positively related to patient hospital satisfaction. Patients form their hospital satisfaction perceptions based on the three facets of their hospital stay experience.
Research limitations/implications
In the spirit of continuous quality improvement, periodically analyzing patient social media comments could help health-care teams understand the patient satisfaction inhibitors that they need to avoid to offer patient-centric care.
Practical implications
By periodically analyzing patient social media comments hospital leaders can quickly identify the gaps in their health service delivery and plug them, which could ultimately give the hospital a competitive advantage.
Originality/value
To the best of the authors’ knowledge, this is one of the first studies to apply mixed methods to patient hospital review comments given freely on social media to critically understand what drives patient hospital satisfaction ratings.
Purpose
This paper aims to reveal the factors patients consider when choosing a doctor for consultation on an online medical consultation (OMC) platform and how these factors influence doctors' consultation volumes.
Design/methodology/approach
In Study 1, influencing factors reflected as service features were identified by applying a feature extraction method to physician reviews, and the importance of each feature was determined based on word frequencies and the PageRank algorithm. Sentiment analysis was used to analyze patient satisfaction with each service feature. In Study 2, regression models were used to analyze the relationships between the service features obtained from Study 1 and the doctor's consultation volume.
Findings
The study identified 14 service features of patients' concerns and found that patients mostly care about features such as trust, phraseology, overall service experience, word of mouth and personality traits, all of which describe a doctor's soft skills. These service features affect patients' trust in doctors, which, in turn, affects doctors' consultation volumes.
Originality/value
This research is important as it informs doctors about the features they should improve, to increase their consultation volume on OMC platforms. Furthermore, it not only enriches current trust-related research in the field of OMC, which has a certain reference significance for subsequent research on establishing trust in online doctor–patient relationships, but it also provides a reference for research concerning the antecedents of trust in general.
Service improvement is of great importance for hotels to gain advantages. Several studies determined the prioritization of service improvement by identifying the relationship between service performance and customer satisfaction but ignored the impact of consumer expectations and managers' subjective opinions. This paper provides an online reviews-driven method for hoteliers to determine the prioritization of improvements in hotel services. Firstly, the improved penalty–reward contrast analysis that quantifies the sentiment tendencies and intensities in online reviews is used to identify types of service attributes. Secondly, based on the categorization of attribute types, three types of consumer expectations that affect consumer satisfaction are mined. Thirdly, the improved three-way decision model is used to determine the priority of allocation resources combining with managers’ subjective opinions. Finally, the proposed method is applied to the case study of Four Seasons Hotel service improvement, and the advantages of this method are illustrated by comparative analysis.
A large volume of patients’ opinions—as online doctor reviews (ODRs)—are available online in order to access, analyze, and improve patients’ perceptions about the quality of care; however, this development needs to be explored further. Drawing on the two-factor theory, this paper aims to mine ODRs to explore the different determinants of patient satisfaction (PS) and patient dissatisfaction (PD) toward the United Kingdom healthcare services. This study collects reviews from a publicly available medical website Iwantgreatcare.org from January 2014 to December 2018, followed by the text mining method based on combining SentiNet and LDA to disclose the semantics of patients’ healthcare experiences. The proposed method found latent topics across the high-risk and low-risk disease category that revealed new insights into what patients value when consulting a physician and what they dislike. For high-risk and low-risk diseases, the determinants of PS were more specific to the hospital business process (hospital environment, location, hospital cafeteria servicescape, parking availability, and medical process, etc.) and doctor-related aspects (physician knowledge, competence, and attitudes, etc.). In contrast, patients’ concerns were most commonly related to their treatment experience and staff bedside manners for both disease categories. Finally, the classification results revealed that the proposed model, which analyzes patient opinion toward different aspects of care, outperformed other state-of-the-art models, with the highest classification F1-score of 88%. The study findings provide a clue for doctors, hospitals, and government officials to enhance PS and minimize PD by addressing their needs and improve the quality of care across different types of diseases, particularly in the current pandemic era of COVID-19.
High-speed rail (HSR) has become an essential mode of public transportation in China and is likely to remain so for the foreseeable future. To promote the development of the HSR industry, a high level of passenger satisfaction must be ensured, which means that passenger satisfaction must be assured. Focusing on HSR in-cabin factors that affect the travel experience of HSR passengers, this study aims to determine passenger demands (PDs) and to evaluate passenger satisfaction by using a combination of online review analysis and large-scale group decision-making (LSGDM). By using web crawler technology, online reviews related to HSR were harvested from a microblogging platform to extract PD data and information. The six PDs that reflect the most frequent concerns of passengers were identified by analyzing the online reviews. The level of satisfaction of passengers with respect to these PDs was analyzed based on the online responses from 100 HSR passengers and by adopting the interval-valued two-tuple linguistic representation model. The final degrees of satisfaction and rankings of the PDs were then determined by using the LSGDM approach with the k-means clustering method and a consensus-reaching process. This research thus constructs an index system of HSR passenger satisfaction evaluation based on online-review analysis and evaluates the process by using LSDGM approaches. The conclusions provide insights into the improvements desired by HSR passengers for in-cabin services and to improve passenger satisfaction.
Health-care waste (HCW) management has been regarded as an increasingly important issue in environmental protection. The evaluation and selection of HCW treatment technologies are essential in HCW management. In this paper, we present a novel group decision making framework based on Z-numbers and the TODIM method to synthesise the opinions of the experts and assist them in selecting an optimal HCW treatment technology. This framework comprises three phases, namely, (I) transformation of decision-making information, (II) determination of the criteria weights and (III) ranking of the alternatives. It can take advantage of Z-numbers to express the opinions of experts and to analyse their reliability. The TODIM method captures the bounded rationality of these experts and enhances the reasonability of the selection. An illustrative example is presented to demonstrate the feasibility of the proposed framework.
With the growing availability and popularity of sentiment-rich resources like blogs and online reviews, new opportunities and challenges have emerged regarding the identification, extraction, and organization of sentiments from user-generated documents or sentences. Recently, many studies have exploited lexicon-based methods or supervised learning algorithms to separately conduct sentiment analysis tasks; however, the former approaches ignore contextual information of sentences and the latter ones do not take sentiment information embedded in sentiment words into consideration. To tackle these limitations, we propose a new model named Sentiment Convolutional Neural Network (SentiCNN) to analyze the sentiments of sentences with both contextual and sentiment information of sentiment words, in which, contextual information is captured from word embeddings and sentiment information is identified using existing lexicons. We incorporate a Highway Network into our model to adaptively combine sentiment and contextual information from sentences by strengthening the connection between features of both sentences and their sentiment words. Furthermore, we propose three lexicon-based attention mechanisms (LBAMs) for our SentiCNN model to find the most important indicators of sentiments and make predictions more effectively. Experiments over two well-known datasets indicate that sentiment words, the Highway Network, and LBAMs contribute to sentiment analysis.
Evaluating patient satisfaction on medical services in terms of multiple aspects is critical for hospital management. To settle this problem, a criteria system for medical service evaluation is first structured through a survey on experts. The probabilistic linguistic representation model is used to portray the qualitative evaluations that are unquantifiable in nature or unable to be accurately measured. Then, the best-worst method is extended to the probabilistic linguistic context to determine the weights of criteria information. Afterwards, we propose a comprehensive method by combing the probabilistic linguistic best-worst method with the gained and lost dominance score method to measure both the collective and worst performances of alternatives. Finally, we investigate a practical case about managing patient satisfaction in the blood collection room of a Chinese hospital which undergoes a reformation. The results show that the patient satisfaction has greatly improved after the reformation.
In the online health community, the doctor-patient interaction is one of the most important functional modules. A large volume of unstructured text data has been generated in the doctor-patient interaction process. This development is worth exploring. In this paper, we mainly explore the influences of online doctor-patient interaction content on patient satisfaction. We collected the online doctor-patient interaction text data from a big online health community (http://haodf.com) in China from January 2015 to December 2016, followed by the use of text mining and econometrics to test our hypotheses. The results indicate that the patient's activeness has a positive effect on a doctor's informational and emotional support. Furthermore, both a doctor's informational and emotional support are known to have a positive effect on patient satisfaction. More significantly, the effect of emotional support on patient satisfaction is more significant than that of informational support. In addition, the patient's disease severity strengthens the link between a doctor's informational and emotional support and that of patient satisfaction. This study has far-reaching significance for a better understanding of the doctor-patient interaction mechanism.
Online customer reviews (OCRs) provide much information about products or service, but the mass of information increases the difficulty for customers to make decisions. Thus, we establish a multi-criteria decision making (MCDM) model to evaluate products or service. To analyze OCRs, the sentiment analysis (SA) is introduced to identify the sentiment orientation of reviews. Considering that the textual information in OCRs is linguistic information, probabilistic linguistic term sets (PLTSs) are applied to present the results of the SA. A process of extracting probabilistic linguistic information based on SA from OCRs is also presented. Then, for the MCDM problems with unknown criteria weights, we combine the PP (projection pursuit) method and the MULTIMOORA (multiplicative multi-objective optimization by ratio analysis) method, and develop an extended method (named as the PP-MULTIMOORA method). The projection pursuit (PP) method is developed to derive objective criteria weights and the MULTIMOORA method is to derive final rankings of products or service. Finally, we apply the proposed model to a case of evaluating doctors’ service quality and further conduct a comparative analysis to illustrate the effectiveness of our work.
This study aims to investigate the hotel selection differences among different types of travellers through online hotel reviews. Specifically, the study performs a detailed examination of the differences in hotel key factors, criterion importance and selection results among five types of travellers, namely, business, couples, families, friends and solo. Using a sample of 194,885 online reviews on TripAdvisor.com, this study identifies the hotel key factors and criterion importance by employing the term frequency-inverse document frequency algorithm and Word2Vec algorithm. Additionally, a bounded rationality behavioural decision support model with picture fuzzy information is proposed to address hotel selection problems for different traveller types. Our results suggest that different types of travellers present differences in hotel key factors, criterion importance and selection results. However, families and friends have similar hotel selection results. This study can serve as a reference for hotel managers in understanding traveller preferences and for tourism website optimisation.
Online product reviews (OPRs) provide abundant information for potential customers to make optimal purchase decisions, and they apply Big Data to better understand product performance. OPRs contain an enormous stockpile of information; therefore, it is difficult for potential customers to make a comprehensive evaluation of alternative products through qualitative reviews. To facilitate consumer purchase decisions, ranking the alternatives based on the OPRs posted on social media platforms is a worthwhile research topic, although relative study is comparatively rare. Therefore, this article provides an extended probabilistic linguistic TODIM (PL-TODIM) method for assisting potential customers to evaluate alternative products through consumer opinions regarding product performance. In other words, this study introduces a novel multiple attribute decision making (MADM) method to rank products based on OPRs. To realize this goal, some basic theories of probabilistic linguistic term sets (PLTSs) are reviewed. Moreover, a possibility formula is first proposed to compare the probabilistic linguistic term sets (PLTSs). Furthermore, a combined weighting method is developed to determine objective weights based on cross-entropy and entropy measures. Thus, the specific steps of the extended PL-TODIM method are described. After that step, in order to testify to the effectiveness and practicality of the proposed method, a case study of OPRs for SUVs is designed. Last, comparisons with other existing methods are further performed to show its advantages.
TODIM (an acronym in Portuguese of interactive and multicriteria decision making), which is founded on nonlinear cumulative prospect theory, has attracted increasing attention from the academic world since 1991. Up to now, a variety of TODIM multicriteria decision models have been developed and applied for solving decision making problems in a wide range of industries. In this study, we point out a limitation of TODIM, which is shared by all the TODIM-based models. Three types of inputs inherent in TODIM, i.e., criteria measurements, criteria weights and the attenuation factor of the losses, are usually uncertain. Moreover, these uncertainties may exist in TODIM at the same time, which has not been well investigated in the literature. To address this limitation, we apply stochastic multiobjective acceptability analysis (SMAA) to TODIM and therefore put forward the SMAA-TODIM method, to explore simultaneously the uncertainties inherent in the inputs of TODIM. In addition, a SMAA-TODIM-based robustness analysis framework for TODIM models is presented, based on which, the decision analyst can measure how robust a decision result is. Finally, applications of the robustness analysis framework for TODIM models are demonstrated by two examples.
Hesitant fuzzy linguistic term set (HFLTS) is a useful tool for describing people's subjective cognitions in the process of decision making. Multiple criteria decision making (MCDM) involves two important steps: (1) determining the criteria weights; (2) obtaining a suitable ranking of alternatives. In this paper, we propose some hesitant fuzzy linguistic entropy and cross-entropy measures, and then establish a model for determining the criteria weights, which considers both the individual effect of each hesitant fuzzy linguistic element (HFLE) and the interactive effect between any two HFLEs with respect to each criterion. Additionally, we give a hesitant fuzzy linguistic alternative queuing method (HFL-AQM) to deal with the MCDM problems. The directed graph and the precedence relationship matrix make the calculation processes and the final results much more intuitive. Finally, a case study concerning the tertiary hospital management is made to verify the weight-determining method and the HFL-AQM.
Healthcare industry in developing countries has recorded high growth rate in the recent years. This study seeks to identify the most critical factors in hospitals related to service quality that will ensure survival and success in the future. This study was conducted using the data from the consumers who received services from 40 different private hospitals in Hyderabad, India. Tangibility, reliability, responsiveness, assurance and empathy (Service Quality dimensions), patient satisfaction and loyalty to the hospital were the variables considered for this study. A path analysis was done on AMOS V20 in order to compute path coefficients, direct and indirect effects of the variables on patient's satisfaction and also loyalty to the hospital. We found that reliability and responsiveness (not empathy, tangibility, and assurance) impact patients’ satisfaction. Patient's satisfaction is directly related to patients’ loyalty to the hospital. Marital status and age have no impact on the regression weights of the variables analyzed; however, it was found that to some extent gender does.
When expressing preferences in qualitative setting, several possible linguistic terms with different weights (represented by probabilities) may be considered at the same time. The probabilistic distribution is usually hard to be provided completely and ignorance may exist. In this paper, we first propose a novel concept called probabilistic linguistic term set (PLTS) to serve as an extension of the existing tools. Then we put forward some basic operational laws and aggregation operators for PLTSs. After that, we develop an extended TOPSIS method and an aggregation-based method respectively for multi-attribute group decision making (MAGDM) with probabilistic linguistic information, and apply them to a practical case concerning strategy initiatives. Finally, the strengths and weaknesses of our methods are clarified by comparing them with some similar techniques.
To gain an understanding of how patient satisfaction (PS) with the doctor (PSD) is conceptualized through an empirical review of how it is currently being measured. The content of PS questionnaire items was examined to (a) determine the primary domains underlying PSD, and (b) summarize the specific doctor-related characteristics and behaviors, and patient-related perceptions, composing each domain.
A scoping review of empirical articles that assessed PSD published from 2000 to November 2013. MEDLINE and PsycINFO databases were searched.
The literature search yielded 1726 articles, 316 of which fulfilled study inclusion criteria. PSD was realized in one of four health contexts, with questions being embedded in a larger questionnaire that assessed PS with either: (1) overall healthcare, (2) a specific medical encounter, or (3) the healthcare team. In the fourth context, PSD was the questionnaire's sole focus. Five broad domains underlying PSD were revealed: (1) Communication Attributes; (2) Relational Conduct; (3) Technical Skill/Knowledge; (4) Personal Qualities; and (5) Availability/Accessibility.
Careful consideration of measurement goals and purposes is necessary when selecting a PSD measure.
The five emergent domains underlying PSD point to potential key areas of physician training and foci for quality assessment.
Copyright © 2015 Elsevier Ireland Ltd. All rights reserved.
This paper surveys the state of the art of sentiment analysis. First, three important tasks of sentiment analysis are summarized and analyzed in detail, including sentiment extraction, sentiment classification, sentiment retrieval and summarization. Then, the evaluation and corpus for sentiment analysis are introduced. Finally, the applications of sentiment analysis are concluded. This paper aims to take a deep insight into the mainstream methods and recent progress in this field, making detailed comparison and analysis. © by Institute of Software, the Chinese Academy of Sciences. All rights reserved.
Patients are increasingly turning to online physician ratings, just as they have sought ratings for other products and services. Much of what is known about these sites comes from studies of the ratings left on them.1 Little is known about the public’s awareness and use of online physician ratings, and whether these sites influence decisions about selecting a physician.
This article presents an evaluation study of residential properties carried out together with real estate agents in the city of Volta Redonda, Brazil. The study aimed to define a reference value for the rents of these properties using the TODIM method of Multicriteria Decision Aiding. By applying this method to the ordering of properties with different characteristics, a ranking of all the properties was obtained and, as a result of this, diverse ranges of rental values for the properties under analysis. The study was complemented by an analysis of the sensitivity of the numerical results obtained.
HanLP: Han language processing
- H He
Automatic acquisition of emotional vocabulary based on syntax
- J-M Chen
- H-F Lin
- Z-H Yang
- Chen J-m
The expansion and application of Chinese emotion word ontology
- H Zhao
Document sentiment orientation analysis based on sentence weighted algorithm
- A-P Li
- P Di
- L-G Duan
- Li A-p