Detecting Topic and Sentiment Trends in Physician Rating Websites: Analysis of Online Reviews Using 3-Wave Datasets

Abstract

(1) Background: Physician rating websites (PRWs) are a rich resource of information where individuals learn other people response to various health problems. The current study aims to investigate and analyze the people top concerns and sentiment dynamics expressed in physician online reviews (PORs). (2) Methods: Text data were collected from four U.S.-based PRWs during the three time periods of 2018, 2019 and 2020. Based on the dynamic topic modeling, hot topics related to different aspects of healthcare were identified. Following the hybrid approach of aspect-based sentiment analysis, the social network of prevailing topics was also analyzed whether people expressed positive, neutral or negative sentiments in PORs. (3) Results: The study identified 30 dominant topics across three different stages which lead toward four key findings. First, topics discussed in Stage III were quite different from the earlier two stages due to the COVID-19 outbreak. Second, based on the keyword co-occurrence analysis, the most prevalent keywords in all three stages were related to the treatment, questions asked by patients, communication problem, patients’ feelings toward the hospital environment, disease symptoms, time spend with patients and different issues related to the COVID-19 (i.e., pneumonia, death, spread and cases). Third, topics related to the provider service quality, hospital servicescape and treatment cost were the most dominant topics in Stages I and II, while the quality of online information regarding COVID-19 and government countermeasures were the most dominant topics in Stage III. Fourth, when zooming into the topic-based sentiments analysis, hot topics in Stage I were mostly positive (joy be the dominant emotion), then negative (disgust be the dominant emotion) in Stage II. Furthermore, sentiments in the initial period of Stage III (COVID-19) were negative (anger be the dominant emotion), then transformed into positive (trust be the dominant emotion) later. The findings also revealed that the proposed method outperformed the conventional machine learning models in analyzing topic and sentiment dynamics expressed in PRWs. (4) Conclusions: Methodologically, this research demonstrates the ability and importance of computational techniques for analyzing large corpora of text and complementing conventional social science approaches.

Measuring Patient Experience and Patient Satisfaction—How Are We Doing It and Why Does It Matter? A Comparison of European and U.S. American Approaches

“…The U.K., for example, already enables patients and hospitals to complement their ratings on NHS Choices with narrative feedback, following the example of social media platforms [ 93 ]. Moreover, current advances in machine learning with improved automatized analysis of qualitative data—as reviews on online platforms are—are bound to facilitate the analysis of such narrative feedback modalities [ 94 ]. However, it must be kept in mind that users of online rating platforms may represent only a specific sociodemographic subgroup of patients and that the survey mode may affect response behavior and be susceptible to manipulation, thus limiting the generalizability of the conclusions obtained of such data [ 95 , 96 ].…”

“…Emerging and increasingly important sources of patient experience, such as website-based feedback from social media or discussion fora, are oftentimes viewed as unreliable sources of information. Nevertheless, studies show that these narrative data can be analyzed [ 94 ] and then yield important additional information such as the reference to additional and underrepresented dimensions of patient experience (i.e., compassion of staff, quality of nursing, facilities, and amenities) that are not yet captured in the conventional questionnaires [ 91 ]. Incorporating such domains into the existing measures could possibly improve the process of evaluating patient experience and satisfaction and provide important feedback to the respective hospitals [ 88 , 91 , 111 ].…”

Topic modeling and sentiment analysis of Chinese people’s attitudes toward volunteerism amid the COVID-19 pandemic

“…First, survey is a time-consuming research method. Traditional surveys usually take months to prepare (Shah et al, 2021). Second, survey data are often biased due to increasingly low response rates (usually well below 10%; Munro, 2018).…”

Exploring public attitudes toward live-streaming fitness in China: A sentiment and content analysis of China's social media Weibo

“…Moreover, the upside of this new method is that online data often unlocks information supporting new insights, particularly in the field of public health. For example, Nobutoshi et al used the largest Japanese Q&A bulletin board service data to analyze public concerns about influenza vaccinations ( 16 ); Shah et al collected data from physician rating websites (PRWS) to investigate people's attitudes toward various health problems ( 17 ), and many more.…”