JMIR Publications

ABSTRACT

Background:

Social media platforms allow individuals to openly gather, communicate, and share information about their interaction with healthcare services, becoming an essential supplemental means of understanding patient experience.

Objective:

To identify common discussion topics about healthcare experience from the public’s perspectives and to determine areas of concern from patients’ perspectives that healthcare providers should take action.

Methods:

This study conducted a spatiotemporal analysis of volume, sentiment, and topic of patient experience related posts on the Weibo platform. We applied a supervised machine learning approach including human annotation and machine learning-based models for topic modelling and sentiment analysis on the public discourse. A multi-classifier voting method based on Logistic Regression, Multinomial Naïve Bayes and Random Forest were used.

Results:

A total of 4,008 posts were manually classified into patient experience topics. A patient experience theme framework was developed. The accuracy, precision, recall, and F-measure of the integration of 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 showed that negative sentiment posts constituted the highest proportion (3319/4008, 82.8%). There are 20 patient experience themes discussed on the social media platform. The majority of posts described the interpersonal aspects of care (73.5%, 2947/4008); the five most frequent discussion topics were “provider attitude”, “access to care”, “communication, information and education”, “technical competence”, and “efficacy of treatment”.

Conclusions:

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, the machine learning algorithm can be used for topic modelling. 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 that patients make a critical evaluation of hospital services.