Professor Susan Michie: Behavioural Science meets Computer Science: The Human Behaviour-Change Project

A seminar by Professor Susan Michie. Room 1.33-1.34. HOsted by D O'Connor.

Behaviour change is essential if major health problems such as obesity and cancer are to be tackled.  Interventions to change behaviour have generally had modest and variable effects. High quality, relevant and cumulative evidence is needed by researchers, policy-makers and practitioners about how interventions vary across contexts, and why. Such evidence is currently produced on a vast but fragmented scale and more rapidly than humans can synthesise and access.  Computers have the capacity and speed to do this task but lack the organisational structure to do this successfully.

The Human Behaviour-Change Project, a collaboration of behavioural scientists, computer scientists and system architects, is building an automated Knowledge System to answer variants of the ‘big question’: ‘What works, compared with what, how well, for whom, in what settings, for what behaviours and why?’ Using Artificial Intelligence (machine learning and reasoning algorithms), the Knowledge System aims to scan the world literature on behaviour change, identify key information and convert this into knowledge. To train the AI system, behavioural scientists are building an organising structure (the Behaviour Change Intervention Ontology) to extract, synthesise and interpret relevant information. This system should be able to (i) answer questions with up-to-date evidence tailored to user need and context and (ii) generate new hypotheses and advance our understanding of human behaviour.