JMIR Publications

ABSTRACT

Background:

Interactions in online mental health communities can reduce psychological distress and significantly enhance members’ mental well-being. The overall quality of support is uneven due to differences in people’s capacities to help others, leading to some problems of support seekers being solved, while others are not.

Objective:

The purpose of this paper is to study which characteristics of the comments posted to offer support can help support seekers (that is, result in cognitive change).

Methods:

This study applied signaling theory to identify antecedents of this cognitive change, and used consulting strategies from the offline, face-to-face psychological counseling process, described in the literature, to construct six characteristics, namely intimacy, emotional polarity, the use of first-person words, the use of words indicating the future, specificity, and language style. We used text mining and natural language processing technology to identify the features in online text, and we used a multiple regression model for empirical analysis.

Results:

The findings show that support comments are more likely to alter support seekers’ cognitive processes if they have lower intimacy, higher positive emotional polarity, lower specificity, more first-person words, more future- and present-tense words, and less function words.

Conclusions:

This work built a model to analyze the factors that make an online mental health community support seeker better. This work has significance for online mental health community support providers. Additionally, it offers pointers for managing and designing online communities for mental health.