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

Author summary Developing effective interventions for health behaviours such as healthy eating and physical activity requires methods that can capture the complex, individual factors shaping people’s everyday experiences, including stress and motivation. Because such factors often fluctuate over time, longitudinal approaches are needed to understand how experiences and behaviours unfold in real-world contexts. For such methods to be effective, they must also be acceptable, engaging, and accessible; particularly for underserved or disadvantaged populations known to experience lower health and digital literacy. In this study, we introduce conversational longitudinal ecological assessment (CLEA), a digital health method that uses conversational AI technology to collect ecologically valid qualitative data over time through an accessible instant-messaging platform. We demonstrate the feasibility, acceptability, and utility of CLEA through a real-world deployment investigating the experiences of individuals accessing a community-based weight management programme, being delivered in an area of deprivation. To support other health researchers, we position CLEA in relation to existing longitudinal qualitative methods and highlight the key design considerations that shape engagement, data quality, and participant experience.