Assessing the influence of mobile health platform ratings and sentiments on perceived treatment efficiency: A data-driven analysis

This study examines the impact of user-generated ratings, sentiment analysis of reviews, reports of symptom improvement, and perceived satisfaction on treatment efficacy in mobile health (mHealth) platforms. Employing a mixed-methods approach, we examined text reviews and ratings from WeDoctor, a prominent Chinese website, integrating computational sentiment analysis with hierarchical regression modeling. The results indicated that comment scores exerted a more significant direct influence on treatment efficiency than sentiment scores; nevertheless, sentiment scores had a crucial indirect effect in enhancing satisfaction. The mention of symptom improvement considerably moderated the impact of comment scores, but not sentiment, indicating that clinical outcomes corroborate quantitative assessments more than emotional expressions. Using a BERT-based sentiment classification model pretrained on Chinese-language reviews, we analyzed the emotional tone of 15000 user-generated consultations. Results showed that 97 % of reviews were classified as positive, indicating a high degree of emotional satisfaction and trust in mHealth service experiences. This affective signal was then integrated with structured ratings and symptom improvement cues to model perceived treatment efficiency. The mixed-methods design leverages both structured and unstructured data, offering a multidimensional perspective that extends traditional Expectation Confirmation Theory to digital healthcare. By combining cognitive, affective, and clinical dimensions of user feedback, the study provides a multifaceted understanding of perceived efficiency. It informs the future design of emotionally intelligent and healthcare-grounded mHealth interfaces, aligning with key priorities in human-computer interaction research. • Uses BERT and regression to assess treatment efficiency in mHealth reviews. • Ratings predict outcomes; sentiment influences efficiency via satisfaction. • Symptom relief boosts rating impact but not sentiment on perceived outcomes. • Reveals cognitive, emotional, and clinical paths in digital health evaluation. • Provides a reproducible framework for mHealth interface design insights.