Analyzing Patient Experience on Weibo: Machine Learning Approach to Topic Modeling and Sentiment Analysis

• Published in: JMIR medical informatics 2024-11, Vol.12, p.e59249-e59249
• Main Authors: Chen, Xiao, Shen, Zhiyun, Guan, Tingyu, Tao, Yuchen, Kang, Yichen, Zhang, Yuxia
• Format: Article
• Language: English
• Subjects: Bayes Theorem; Data collection; Data mining; Hospitals; Humans; Machine Learning; Observational studies; Patient Satisfaction; Quality improvement; Sentiment analysis; Social Media; Social networks; User behavior; User generated content
• ISSN: 2291-9694; 2291-9694
• DOI: 10.2196/59249

Social media platforms allow individuals to openly gather, communicate, and share information about their interactions with health care services, becoming an essential supplemental means of understanding patient experience. We aimed to identify common discussion topics related to health care experience from the public's perspective and to determine areas of concern from patients' perspectives that health care providers should act on. This study conducted a spatiotemporal analysis of the volume, sentiment, and topic of patient experience-related posts on the Weibo platform developed by Sina Corporation. We applied a supervised machine learning approach including human annotation and machine learning-based models for topic modeling and sentiment analysis of the public discourse. A multiclassifier voting method based on logistic regression, multinomial naïve Bayes, and random forest was used. A total of 4008 posts were manually classified into patient experience topics. A patient experience theme framework was developed. The accuracy, precision, recall, and F-measure of the method integrating logistic regression, multinomial naïve Bayes, and random forest for patient experience themes were 0.93, 0.95, 0.80, 0.77, and 0.84, respectively, indicating a satisfactory prediction. The sentiment analysis revealed that negative sentiment posts constituted the highest proportion (3319/4008, 82.81%). Twenty patient experience themes were discussed on the social media platform. The majority of the posts described the interpersonal aspects of care (2947/4008, 73.53%); the five most frequently discussed topics were "health care professionals' attitude," "access to care," "communication, information, and education," "technical competence," and "efficacy of treatment." Hospital administrators and clinicians should consider the value of social media and pay attention to what patients and their family members are communicating on social media. To increase the utility of these data, a machine learning algorithm can be used for topic modeling. The results of this study highlighted the interpersonal and functional aspects of care, especially the interpersonal aspects, which are often the "moment of truth" during a service encounter in which patients make a critical evaluation of hospital services.