Conversational, Longitudinal, Ecological Assessment (CLEA): Exploring a new AI-driven method for qualitative data collection in a behavioural health context.

Abstract

In this paper, we present conversational longitudinal ecological assessment (CLEA), a novel conversational AI-enabled method for collecting ecologically valid, temporally sensitive qualitative health data via mobile instant messaging. We report findings from an exploratory deployment of an instantiation of CLEA within a 12-week community-based weight management programme, delivered by a charity partner in an area of deprivation. Using WhatsApp, we deployed our CLEA chat-agent to conduct twice-weekly conversational data collection sessions with participants, to elicit data about their experience of the programme and associated behaviour change. This was followed by in-person semi-structured interviews (N = 9) to examine user experiences and perceptions of interacting with the chat-agent. Participants reported that WhatsApp's familiarity supported accessibility and sustained engagement, while the conversational format encouraged reflection directed towards the research focus. Responding to chat-agent prompts required cognitive effort, leading some participants to defer engagement until they had adequate time and mental space; however, this reflective demand was largely experienced as beneficial within the programme context. The AI's quasi-human interactional qualities fostered a sense of support while reducing social judgement, enabling more candid disclosure. Together, these findings suggest initial feasibility and acceptability of this CLEA implementation within a community-based programme in an area of deprivation. Further, while the responses in single messages were often brief, useful, relevant, and meaningful insights appeared to develop over the course of conversational sessions. The study highlights both the opportunities and trade-offs of conversational AI for qualitative data collection, including design implications for health researchers looking to implement or extend the method. Finally, we position CLEA in relation to other longitudinal methods of qualitative health data elicitation.