Decoding Mental Health Conversations with GenAI

The exploratory study examined the types of utterances that initiate mental health conversations with GenAI, the main elements of the system’s responses, and user reactions to them. A structured diary was used by participants to record their interactions with a GenAI chatbot for one week. Participants also discussed their experiences in an end-of-study focus group. Thematic analysis was applied to the collected qualitative data. The findings indicate that the primary input types included venting negative emotions and seeking information. System-generated responses included elements of empathy/acknowledgment, information, and/or follow-up questions to continue the conversation. In assessing AI responses, participants valued emotional support, the system’s ability to produce a natural conversational flow, and its ability to offer personalized information. Participants praised the system’s ability to recall and build on prior conversations. Participants expect GenAI to provide support that balances emotional validation with high-quality information, delivered through a human-like conversational flow. The study developed a novel classification of the types of needs users aim to address during mental health interactions with a chatbot, as well as the elements of GenAI responses that users value. The findings inform further work on developing requirements and testing mechanisms for GenAI systems’ performance in the mental health context.