The Impact of Linguistic Signals on Cognitive Change in Support Seekers in Online Mental Health Communities: Text Analysis and Empirical Study

作者：M. H. Li, Dongxiao Gu, Rui Li, Yadi Gu, Hu Liu, Kaixiang Su, Xiaoyu Wang, Gongrang Zhang · 发表于：Journal of Medical Internet Research · 年份：2025 · DOI：10.2196/60292 · 被引用次数：7 · 研究领域：Mental Health via Writing、Digital Mental Health Interventions、Mental Health Treatment and Access

Background In online mental health communities, the interactions among members can significantly reduce their psychological distress and enhance their mental well-being. The overall quality of support from others varies due to differences in people’s capacities to help others. This results in some support seekers’ needs being met, while others remain unresolved. Objective This study aimed to examine which characteristics of the comments posted to provide support can make support seekers feel better (ie, result in cognitive change). Methods We used signaling theory to model the factors affecting cognitive change and used consulting strategies from the offline, face-to-face psychological counseling process to construct 6 characteristics: intimacy, emotional polarity, the use of first-person words, the use of future-tense words, specificity, and language style. Through text mining and natural language processing (NLP) technology, we identified linguistic features in online text and conducted an empirical analysis using 12,868 online mental health support reply data items from Zhihu to verify the effectiveness of those features. Results The findings showed that support comments are more likely to alter support seekers’ cognitive processes if those comments have lower intimacy (βintimacy=–1.706, P<.001), higher positive emotional polarity (βemotional_polarity=.890, P<.001), lower specificity (βspecificity=–.018, P<.001), more first-person words (βfirst-person=.120, P<....