Examining the Role of Physician Characteristics in Web-Based Verified Primary Care Physician Reviews: Observational Study.

BACKGROUND: Doctor review websites have become increasingly popular as a source of information for patients looking to select a primary care provider. Zocdoc is one such platform that allows patients to not only rate and review their experiences with doctors but also directly schedule appointments. This study examines how several physician characteristics including gender, age, race, languages spoken in a physician's office, education, and facial attractiveness impact the average numerical rating of primary care doctors on Zocdoc. OBJECTIVE: The aim of this study was to investigate the association between physician characteristics and patient satisfaction ratings on Zocdoc. METHODS: A data set of 1455 primary care doctor profiles across 30 cities was scraped from Zocdoc. The profiles contained information on the physician's gender, education, and languages spoken in their office. Age, facial attractiveness, and race were imputed from profile pictures using commercial facial analysis software. Each doctor profile listed an average overall satisfaction rating, bedside manner rating, and wait time rating from verified patients. Descriptive statistics, the Wilcoxon rank sum test, and multivariate logistic regression were used to analyze the data. RESULTS: The average overall rating on Zocdoc was highly positive, with older age, lower facial attractiveness, foreign degrees, allopathic degrees, and speaking more languages negatively associated with the average rating. However, the effect sizes of these factors were relatively small. For example, graduates of Latin American medical schools had a mean overall rating of 4.63 compared to a 4.77 rating for US graduates (P<.001), a difference roughly equivalent to a 2.8% decrease in appointments. On multivariate analysis, being Asian and having a doctor of osteopathic medicine degree were positively associated with higher overall ratings, while attending a South Asian medical school and speaking more European and Middle Eastern languages in the office were negatively associated with higher overall ratings. CONCLUSIONS: Overall, the findings suggest that age, facial attractiveness, education, and multilingualism do have some impact on web-based doctor reviews, but the numerical effect is small. Notably, bias may play out in many forms. For example, a physician's appearance or accent may impact a patient's trust, confidence, or satisfaction with their physician, which could in turn influence their take-up of preventative services and lead to either better or worse health outcomes. The study highlights the need for further research in how physician characteristics influence patient ratings of care.

Leveraging employee online reviews for improving hotel competitiveness in the great resignation.

The Great Resignation has brought significant challenges to the recovery of the hospitality industry from the depression caused by the coronavirus pandemic (COVID-19). Prior studies have revealed that the leading cause of the Great Resignation is negative employee experience. However, few empirical studies have been conducted to obtain deep insights into the negative experiences of hospitality employees. Hotel managers still lack the knowledge to help them resolve the workforce problem and maintain competitiveness during the pandemic. This study proposes a novel framework, named HENEX, that uses data-mining technologies and employees' online reviews about hotels to identify the factors that lead to hospitality employees' negative experiences and changes in these factors caused by COVID-19. We demonstrate the effectiveness of HENEX through a case study that involves major hotels in Australia. The findings could help hotel managers develop strategies to resolve the workforce problem and maintain competitiveness during the Great Resignation period.

Consumers' satisfaction factors mining and sentiment analysis of B2C online pharmacy reviews.

BACKGROUND: In recent years, online pharmacies have been accepted by increasingly more consumers, and the prospects for online pharmacies are optimistic. This article explores the consumers' satisfaction factors addressed in Business to Customer (B2C) online pharmacy reviews and analyzes the sentiments expressed in the reviews. The goal of this work is to help B2C online pharmacy enterprises identify consumers' concerns, continuously improve the health services level. METHODS: This article was based on the Latent Dirichlet Allocation (LDA) topic model. From a third-party platform-based B2C online pharmacy and a proprietary B2C online pharmacy (JD Pharmacy and J1.COM, respectively), 136,630 pieces of over-the-counter (OTC) drug review data posted from January 1, 2015 to December 31, 2018 were selected as samples and used to explore the satisfaction factors of B2C online pharmacy consumers regarding the entire drug purchasing process. Then, the sentiments expressed in the drug reviews were analyzed with SnowNLP. RESULT: Categorization of the 12 factors identified by LDA showed that 5 factors were related to logistics; these 5 factors, which also included the most drug reviews, made up 38.5% of the reviews. The number of factors related to drug prices was second, with 3 factors, and reviews of drug prices made up 25.5% of the reviews. Customer service and drug effects each had two related factors, and a smaller percentage of these reviews (13.95%) were related to drug effects. Consumers still maintain positive opinions of JD Pharmacy and J1.COM. However, some opinions on logistics and drug prices are expressed. CONCLUSION: The most important task for online pharmacies is to improve logistics. It is better to develop self-built logistics. Both types of B2C online pharmacies can improve consumer viscosity by implementing marketing strategies. With regard to customer service, focusing on improving employees' service attitudes is necessary.

What Do Patients Say About Doctors Online? A Systematic Review of Studies on Patient Online Reviews.

BACKGROUND: The number of patient online reviews (PORs) has grown significantly, and PORs have played an increasingly important role in patients' choice of health care providers. OBJECTIVE: The objective of our study was to systematically review studies on PORs, summarize the major findings and study characteristics, identify literature gaps, and make recommendations for future research. METHODS: A major database search was completed in January 2019. Studies were included if they (1) focused on PORs of physicians and hospitals, (2) reported qualitative or quantitative results from analysis of PORs, and (3) peer-reviewed empirical studies. Study characteristics and major findings were synthesized using predesigned tables. RESULTS: A total of 63 studies (69 articles) that met the above criteria were included in the review. Most studies (n=48) were conducted in the United States, including Puerto Rico, and the remaining were from Europe, Australia, and China. Earlier studies (published before 2010) used content analysis with small sample sizes; more recent studies retrieved and analyzed larger datasets using machine learning technologies. The number of PORs ranged from fewer than 200 to over 700,000. About 90% of the studies were focused on clinicians, typically specialists such as surgeons; 27% covered health care organizations, typically hospitals; and some studied both. A majority of PORs were positive and patients' comments on their providers were favorable. Although most studies were descriptive, some compared PORs with traditional surveys of patient experience and found a high degree of correlation and some compared PORs with clinical outcomes but found a low level of correlation. CONCLUSIONS: PORs contain valuable information that can generate insights into quality of care and patient-provider relationship, but it has not been systematically used for studies of health care quality. With the advancement of machine learning and data analysis tools, we anticipate more research on PORs based on testable hypotheses and rigorous analytic methods. TRIAL REGISTRATION: International Prospective Register of Systematic Reviews (PROSPERO) CRD42018085057; https://www.crd.york.ac.uk/PROSPERO/display_record.php?RecordID=85057 (Archived by WebCite at http://www.webcitation.org/76ddvTZ1C).

Automation framework for online review of daily dose distributions using CT on Rails in proton therapy.

PURPOSE: To demonstrate a framework for calculating daily dose distributions for proton therapy in a timeframe amenable to online evaluation using CT-on-Rails. METHODS: Tasks associated with calculation of daily dose are fully automated. A rigid registration between daily and planning images is used to propagate beams and targets for calculation of daily dose; additionally, risk structures are propagated using deformable registration to facilitate online evaluation. An end-to-end constancy test was carried out using a pelvis phantom containing a simulated target and bladder contour. 97 Daily fan-beam CT data sets associated with 10 clinical patients were processed to demonstrate feasibility and utility of online evaluation. Computing times and dosimetric differences are reported. RESULTS: The phantom constancy test took 62 s to complete with no notable discrepancies in the registrations or calculated dose. Max doses were identical for target and bladder contours on initial and repeat scans (359 and 310 cGy (RBE) respectively). Total processing time for 97 daily patient images averaged 154.6 s (73.0 - 222.0 s; SD = 31.8 s). On average, dose calculation accounted for 35 % of total processing time. Average differences in D95 for target contours was 1.5 % (SD = 1.6 %) with a max decrease of 5.9 % on a single daily image. CONCLUSION: Daily dose can be automatically calculated in a timeframe amenable to online evaluation using scanner utilities in conjunction with the scripting API of a commercial treatment planning system. Online evaluation of dose in proton therapy is useful to detect clinically relevant changes, guide setup, and facilitate treatment or replanning decisions.

Exploring sources of patient dissatisfaction in mobile health communication: A text analysis based on structural topic model.

Understanding online patient dissatisfaction is essential for improving the quality of healthcare services, patient satisfaction, and physician career development. This study is the first to apply the structural topic model to patient satisfaction research based on patient online reviews from a mobile health communication platform, revealing eight negative topics of patient concerns. These topics include under-explored areas such as "go to the hospital for check-ups," "incomplete counseling," and "language expression." Additionally, we incorporated the doctor's title as a covariate in the model to examine how specific topics varied across different conditions. The results indicated that higher-titled doctors were more likely to receive complaints about the cost of treatment and whether the question was answered, whereas lower-titled doctors were more likely to receive complaints related to physician's knowledge, incomplete counseling, and response speed. This study not only enhances our understanding of mobile health services but also provides targeted insights for healthcare providers to improve their services, thereby contributing to the advancement of patient-centered care.

Sentiment analysis of restaurant customer satisfaction during COVID-19 pandemic in Pattaya, Thailand.

The tourism and hospitality industry, particularly the restaurant business, has been greatly affected by the COVID-19 pandemic. To comprehend customer behavior and preferences during this unprecedented time, it is crucial to analyze online restaurant customer reviews. Thus, this study utilized the valence aware dictionary for sentiment reasoning (VADER) model to examine TripAdvisor reviews of restaurants in Pattaya City, Chon Buri, Thailand, covering the period 2017-2022, which encompasses both pre-pandemic and pandemic years. The findings reveal a significant decrease in the number of reviews and a notable increase in negative sentiments during the COVID-19 pandemic compared to normal circumstances. We noticed two concern areas, i.e., service and staff, and food and taste, that should be addressed urgently. The findings of this study offer valuable insights into customer behavior and requirements, thereby empowering restaurant businesses to enhance service quality, satisfy customer requirements, and strategically plan for a post-COVID-19 future.

Integrating big data and marketing concepts into tourism, hospitality operations and strategy development.

Big data (BD) research articles are on new issues, this study sought to fill the knowledge gap of linkage the relationships between big data and marketing strategy with comprehensive viewpoints across different research fields in tourism and hospitality literatures. Content analysis was conducted to gather materials from the particular studies. For each study, the content analysis included the title, abstract, journal, type of sample, exploration design, statistical and analytical techniques, data collection process and keywords was also conducted to confirm the main results of the criteria. The research shows that big data adds value to marketing strategies by using social media to collect information from consumers, which is complemented with appropriate evidence relevant to predicting their needs and behaviors.

Association Between Online Reviews of Substance Use Disorder Treatment Facilities and Drug-Induced Mortality Rates: Cross-Sectional Analysis.

BACKGROUND: Drug-induced mortality across the United States has continued to rise. To date, there are limited measures to evaluate patient preferences and priorities regarding substance use disorder (SUD) treatment, and many patients do not have access to evidence-based treatment options. Patients and their families seeking SUD treatment may begin their search for an SUD treatment facility online, where they can find information about individual facilities, as well as a summary of patient-generated web-based reviews via popular platforms such as Google or Yelp. Web-based reviews of health care facilities may reflect information about factors associated with positive or negative patient satisfaction. The association between patient satisfaction with SUD treatment and drug-induced mortality is not well understood. OBJECTIVE: The objective of this study was to examine the association between online review content of SUD treatment facilities and drug-induced state mortality. METHODS: A cross-sectional analysis of online reviews and ratings of Substance Abuse and Mental Health Services Administration (SAMHSA)-designated SUD treatment facilities listed between September 2005 and October 2021 was conducted. The primary outcomes were (1) mean online rating of SUD treatment facilities from 1 star (worst) to 5 stars (best) and (2) average drug-induced mortality rates from the Centers for Disease Control and Prevention (CDC) WONDER Database (2006-2019). Clusters of words with differential frequencies within reviews were identified. A 3-level linear model was used to estimate the association between online review ratings and drug-induced mortality. RESULTS: A total of 589 SAMHSA-designated facilities (n=9597 reviews) were included in this study. Drug-induced mortality was compared with the average. Approximately half (24/47, 51%) of states had below average ("low") mortality rates (mean 13.40, SD 2.45 deaths per 100,000 people), and half (23/47, 49%) had above average ("high") drug-induced mortality rates (mean 21.92, SD 3.69 deaths per 100,000 people). The top 5 themes associated with low drug-induced mortality included detoxification and addiction rehabilitation services (r=0.26), gratitude for recovery (r=-0.25), thankful for treatment (r=-0.32), caring staff and amazing experience (r=-0.23), and individualized recovery programs (r=-0.20). The top 5 themes associated with high mortality were care from doctors or providers (r=0.24), rude and insensitive care (r=0.23), medication and prescriptions (r=0.22), front desk and reception experience (r=0.22), and dissatisfaction with communication (r=0.21). In the multilevel linear model, a state with a 10 deaths per 100,000 people increase in mortality was associated with a 0.30 lower average Yelp rating (P=.005). CONCLUSIONS: Lower online ratings of SUD treatment facilities were associated with higher drug-induced mortality at the state level. Elements of patient experience may be associated with state-level mortality. Identified themes from online, organically derived patient content can inform efforts to improve high-quality and patient-centered SUD care.

Explaining reviewing effort: Existing reviews as potential driver.

Online review systems try to motivate reviewers to invest effort in writing reviews, as their success crucially depends on the helpfulness of such reviews. Underlying cognitive mechanisms, however, might influence future reviewing effort. Accordingly, in this study, we analyze whether existing reviews matter for future textual reviews. From analyzing a dataset from Google Maps covering 40 sights across Europe with over 37,000 reviews, we find that textual reviewing effort, as measured by the propensity to write an optional textual review and (textual) review length, is negatively related to the number of existing reviews. However, and against our expectations, reviewers do not increase textual reviewing effort if there is a large discrepancy between the existing rating valence and their own rating. We validate our findings using additional review data from Yelp. This work provides important implications for online platforms with review systems, as the presentation of review metrics matters for future textual reviewing effort.

Preference Characteristics on Consumers' Online Consumption of Fresh Agricultural Products under the Outbreak of COVID-19: An Analysis of Online Review Data Based on LDA Model.

Since the outbreak of the COVID-19 pandemic in 2020, China has adopted a zero-clearing policy under closed control. It is rather common for residents who are quarantined at home to buy fresh agricultural products online, when COVID-19 spread in big cities. Many e-commerce platforms are trying to develop online shopping channels for fresh agricultural products. However, negative comments and news about those platforms have been increasing because of several reasons, such as the difference in the quality of fresh products, inadequate categories of commodity and inefficient delivery caused by the shortage of personnel and so on. The smooth daily supply of online fresh agricultural products is conducive to soothing the pessimistic emotions and to encouraging their active obedience to epidemic prevention and control policy. Therefore, it is of great importance to explore the preference characteristics of consumers' online purchase of fresh agricultural products under this critical situation. In this paper, firstly, Pycharm software is used to collect online comment texts of fresh agricultural products on the online platforms with a total of 34,546 pieces of evaluation data. Secondly, the collected data is preformed into the text preprocessing. To be specific, the obtained online comments are processed by Python, including the process of text duplication between sentences, text duplication within sentences and short sentence filtering. After that, processed texts are subjected to Jieba Text Segmentation to form the final word frequency ranking, involving two procedures, part-of-speech tagging and stop-words removal. Lastly, the results of the LDA model indicate the factors that influence consumers' preferences when they purchase fresh agricultural products online. This study could not only identify the typical features of residents' online shopping preference in the context of the spread of COVID-19, but also provide pragmatic suggestions for the local government to appease the residents' negative emotions for the prevention of widespread complaints at the social level.

How do extrinsic cues influence consumers' online hotel booking decisions? An event-related potential experiment.

Booking decision is a typical decision-making behavior in hospitality, while the neural processing of it is still unclear. To address this issue, with the help of event-related potential (ERP), this work uncovered the neural mechanism of the influence of two extrinsic cues, namely, brand familiarity (familiar vs. unfamiliar) and online reviews (positive vs. negative) on online hotel booking decisions. Behavioral results indicated that the booking rate under the condition of positive reviews was higher than that of negative reviews. In addition, the response time in the case of familiar brands was longer than that of unfamiliar brands. ERP results showed that the P200 amplitude of familiar brands was smaller than that of unfamiliar brands, while for the late positive potential amplitude, the opposite was the case. It is suggested that in the early stage of cognitive processing, unfamiliar brands evoke more automatic and unconscious attention while in the later stage, familiar brands attract more conscious attention. This study also found that the N400 amplitude of negative online reviews was larger than that of positive online reviews, indicating that negative stimuli can result in a larger emotional conflicts than that of positive stimuli. This study provides new insights into the neural mechanism of online booking decisions in the hospitality.

Coordinating supply-related scarcity appeals with online reviews.

Online reviews play an important role in consumer purchase decisions and have received much research attention. However, previous research has typically examined the effects of online review characteristics independent of firm marketing messages. We argue that how much average review rating influences consumers' decisions depends on the presence of a scarcity appeal and its congruence with review volume information. Through a lab experiment and analyses of real-world data from Amazon.com, we show that claiming a product to have limited supply moves consumers toward more heuristic processing but only when review volume is consistent with the scarcity information. In contrast, when review volume is incongruent with the supply-based scarcity message, the incongruence prompts consumers to process information more carefully and reduces their reliance on review valence.

Design is More Than Looks: Research on the Affordance of Review Components on Consumer Loyalty.

Background: Online review system contains multiple components, such as ratings, review text, product pictures, and video uploads, that could affect consumer loyalty. However, how the affordance of such components influences perceptions and behaviors of consumers remains unclear. We extend stimulus-organism-response (S-O-R) theory to the online review system. Specifically, we combine affordance theory and the technology acceptance model (TAM) to investigate the relations among the affordance of review systems, consumers' perceived beliefs, and their loyalty. Methods: We surveyed 320 customers on their online shopping experiences in China. We tested our hypotheses using the partial least squares path structural equation modeling (PLS-SEM) method. We report the direct effect of affordances of review components on consumer loyalty and its indirect effects on consumer loyalty through perceived beliefs. Results: Our results show that integrity and social interaction affordance of review components have significant relations with perceived ease of use, perceived usefulness, and perceived enjoyment. Intelligent topic mining reveals a positive relation on perceived enjoyment. Operability has a positive relation with perceived ease of use and perceived usefulness. These three consumer-perceived beliefs can mediate, to different degrees, the relationship between affordance of review components and consumer loyalty. Conclusion: This research takes an innovative approach to offer insights into the relationships between IT affordances and consumer perceptions. We examine S-O-R theory through the lens of information technology and extend S-O-R theory by integrating IT affordances. Our research findings pave the way for businesses to design and implement more effective online review systems.

Factors influencing consumers' willingness to accept service robots: Based on online reviews of Chinese hotels.

The application of robots in service industry is increasing. Compared with related studies in other countries, the research on users' acceptance of mid-range and high-range hotel service robots in China is preliminary. Based on the interaction between Chinese consumers and hotel service robots, this study explored the factors that influence consumers' willingness to accept robots in human-robot interaction. According to the service robot integration willingness scale (performance efficacy, intrinsic motivation, anthropomorphism, social influence, facilitating conditions, and emotion), this study conducted content analysis and sentiment analysis on 4,107 online reviews from 68 mid-range and high-range hotels in Qunar. The results showed that users' overall evaluation of robot service in mid-range and high-range hotels is positive. The most frequently mentioned dimension by users is performance efficacy, followed by intrinsic motivation, anthropomorphism, and emotion, finally, the facilitating conditions, the five dimensions have positive impact on users' evaluation of service robots; the influence of social influence on human-robot interaction evaluation has not been found. This study supplements the research on service robot and provides a reference for hotel managers to make decisions.

Patient Utilization of Online Information and its Influence on Orthopedic Surgeon Selection: Cross-sectional Survey of Patient Beliefs and Behaviors.

BACKGROUND: Patient attitudes and behavior are critical to understand owing to the increasing role of patient choice. There is a paucity of investigation into the perceived credibility of online information and whether such information impacts how patients choose their surgeons. OBJECTIVE: The purpose of this study was to explore the attitudes and behavior of patients regarding online information and orthopedic surgeon selection. Secondary purposes included gaining insight into the relative importance of provider selection factors, and their association with patient age and education level. METHODS: This was a cross-sectional study involving five multispecialty orthopedic surgery groups. A total of 329 patients who sought treatment by six different orthopedic surgeons were asked to anonymously answer a questionnaire consisting of 25 questions. Four questions regarded demographic information, 10 questions asked patients to rate the importance of specific criteria regarding the selection of their orthopedic surgeon (on a 4-point Likert scale), and 6 questions were designed to determine patient attitude and behaviors related to online information. RESULTS: Patient-reported referral sources included the emergency room (29/329, 8.8%), friend (42/329, 12.8%), insurance company (47/329, 14.3%), internet search/website (28/329, 8.5%), primary care physician (148/329, 45.0%), and other (34/329, 10.3%). Among the 329 patients, 130 (39.5%) reported that they searched the internet for information before their first visit. There was a trend of increased belief in online information to be accurate and complete in younger age groups (P=.02). There was an increased relative frequency in younger groups to perceive physician rating websites to be unbiased (P=.003), provide sufficient patient satisfaction information (P=.01), and information about physician education and training (P=.03). There was a significant trend for patients that found a surgeon's website to be useful (P<.001), with the relative frequency increased in younger age groups. CONCLUSIONS: This study shows that insurance network, physician referrals, appointment availability, and office location are important to patients, whereas advertising and internet reviews by other patients were considered to be not as helpful in choosing an orthopedic surgeon. Future studies may seek to identify obstacles to patients in integrating online resources for decision-making and strategies to improve health-seeking behaviors.

"Scapegoat" for Offline Consumption: Online Review Response to Social Exclusion.

Previous research has mostly focused on Internet use behaviors, such as usage time of the Internet or social media after individuals experienced offline social exclusion. However, the extant literature has ignored online response behaviors, such as online review responses to social exclusion. To address this gap, drawing on self-protection and self-serving bias, we proposed three hypotheses that examine the effect of offline social exclusion on online reviews, which are verified by two studies using different simulating scenarios with 464 participants. The results show that when individuals are socially excluded offline, regardless of where the exclusion comes from (businesses or peers), they will be more likely to give negative online reviews. In addition, brand awareness moderates the effect of offline social exclusion on online reviews. Specifically, if the brand is less known, compared with social inclusion, offline social exclusion will lead individuals to give more negative online reviews; conversely, for well-known brands, no significant difference exists in the online reviews between social exclusion and inclusion.

Definition of customer requirements in big data using word vectors and affinity propagation clustering.

Customer requirements (CRs) have a significant impact on product design. The existing methods of defining CRs, such as customer surveys and expert evaluations, are time-consuming, inaccurate and subjective. This paper proposes an automatic CRs definition method based on online customer product reviews using the big data analysis. Word vectors are defined using a continuous bag of words (CBOW) model. Online customer reviews are searched by a crawling method and filtered by the parts of speech and frequency of words. Filtered words are then clustered into groups by an affinity propagation (AP) clustering method based on trained word vectors. Exemplars in each clustering group are finally used to define CRs. The proposed method is verified by case studies of defining CRs for product design. Results show that the proposed method has better performance to determine CRs compared to existing CRs definition methods.

Patient Satisfaction and Hospital Quality of Care Evaluation in Malaysia Using SERVQUAL and Facebook.

Social media sites, dubbed patient online reviews (POR), have been proposed as new methods for assessing patient satisfaction and monitoring quality of care. However, the unstructured nature of POR data derived from social media creates a number of challenges. The objectives of this research were to identify service quality (SERVQUAL) dimensions automatically from hospital Facebook reviews using a machine learning classifier, and to examine their associations with patient dissatisfaction. From January 2017 to December 2019, empirical research was conducted in which POR were gathered from the official Facebook page of Malaysian public hospitals. To find SERVQUAL dimensions in POR, a machine learning topic classification utilising supervised learning was developed, and this study's objective was established using logistic regression analysis. It was discovered that 73.5% of patients were satisfied with the public hospital service, whereas 26.5% were dissatisfied. SERVQUAL dimensions identified were 13.2% reviews of tangible, 68.9% of reliability, 6.8% of responsiveness, 19.5% of assurance, and 64.3% of empathy. After controlling for hospital variables, all SERVQUAL dimensions except tangible and assurance were shown to be significantly related with patient dissatisfaction (reliability, p < 0.001; responsiveness, p = 0.016; and empathy, p < 0.001). Rural hospitals had a higher probability of patient dissatisfaction (p < 0.001). Therefore, POR, assisted by machine learning technologies, provided a pragmatic and feasible way for capturing patient perceptions of care quality and supplementing conventional patient satisfaction surveys. The findings offer critical information that will assist healthcare authorities in capitalising on POR by monitoring and evaluating the quality of services in real time.

Assessing Patient-Perceived Hospital Service Quality and Sentiment in Malaysian Public Hospitals Using Machine Learning and Facebook Reviews.

Social media is emerging as a new avenue for hospitals and patients to solicit input on the quality of care. However, social media data is unstructured and enormous in volume. Moreover, no empirical research on the use of social media data and perceived hospital quality of care based on patient online reviews has been performed in Malaysia. The purpose of this study was to investigate the determinants of positive sentiment expressed in hospital Facebook reviews in Malaysia, as well as the association between hospital accreditation and sentiments expressed in Facebook reviews. From 2017 to 2019, we retrieved comments from 48 official public hospitals' Facebook pages. We used machine learning to build a sentiment analyzer and service quality (SERVQUAL) classifier that automatically classifies the sentiment and SERVQUAL dimensions. We utilized logistic regression analysis to determine our goals. We evaluated a total of 1852 reviews and our machine learning sentiment analyzer detected 72.1% of positive reviews and 27.9% of negative reviews. We classified 240 reviews as tangible, 1257 reviews as trustworthy, 125 reviews as responsive, 356 reviews as assurance, and 1174 reviews as empathy using our machine learning SERVQUAL classifier. After adjusting for hospital characteristics, all SERVQUAL dimensions except Tangible were associated with positive sentiment. However, no significant relationship between hospital accreditation and online sentiment was discovered. Facebook reviews powered by machine learning algorithms provide valuable, real-time data that may be missed by traditional hospital quality assessments. Additionally, online patient reviews offer a hitherto untapped indication of quality that may benefit all healthcare stakeholders. Our results confirm prior studies and support the use of Facebook reviews as an adjunct method for assessing the quality of hospital services in Malaysia.