Xitong Li, Ran (Alan) Zhang, Yuanhong Ma and Shengjun Mao
Additional contact information
Xitong Li: HEC Paris
Ran (Alan) Zhang: Texas Tech University - Area of Information Systems and Quantitative Sciences (ISQS)
Yuanhong Ma: School of Economics and Management, Beihang University
Shengjun Mao: University of Hong Kong - Faculty of Business and Economics
Abstract: While Online Medical Consultation (OMC) platforms offer patients convenient and accessible healthcare services, challenges remain in ensuring effective communication between physicians and patients. Several OMC platforms provide physicians with a voice reply function, enabling them to send voice messages during consultations. This study aims to examine the effectiveness of such an ITenabled function. We integrate media synchronicity theory (MST) and social support theory (SST) to develop a conceptual framework, highlighting how different media with various capabilities influence OMC performance by enabling physicians to convey specific components of social support. Specifically, we analyze data from a leading OMC platform in China to assess the impact of physicians' adoption of voice messages on OMC outcomes. The empirical results show that when physicians use voice messages to respond to patients, patients are more likely to report higher satisfaction and perceive the consultation as more helpful. To explore the underlying mechanisms, we develop advanced deep learning models to extract key factors of emotional support and informational support within OMC interactions. By conducting moderation analyses, we find that voice messages are particularly effective in conveying emotional support components like empathy and affirmation, as well as concrete informational support, which enhances the effects of voice-message use on OMC performance. Our findings suggest that healthcare stakeholders can strategically leverage the voice message feature to improve online consultation outcomes.
Keywords: Voice Messages; Media Performance; Online Medical Consultations; Patient Satisfaction; Perceived Helpfulness; Deep Learning
40 pages, December 10, 2025
Full text files
papers.cfm?abstract_id=5890302 HTML file Full text
Questions (including download problems) about the papers in this series should be directed to Antoine Haldemann ()
Report other problems with accessing this service to Sune Karlsson ().
RePEc:ebg:heccah:1592This page generated on 2026-03-04 15:38:56.