The Human Behaviour Change Project: harnessing computer science to advance behavioural science

Abstract

Behaviour change is essential if major health problems such as obesity and cancer are to be tackled. Evidence is needed by researchers, policy-makers and practitioners about intervention effectiveness across contexts, and about mechanisms of action. 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. Progress in this area requires a collaboration between computer and behavioural scientists to develop a knowledge structure (‘ontology’) and apply it to the evidence, and information science to support the curation and access of evidence. The Human Behaviour Change Project brings together behavioural, computer and information scientists to build an Artificial Intelligence system to continually scan the world literature on behaviour change, extract key information and use this to build and update the scientific understanding of human behaviour to answer variants of the ‘big question’: ‘What works, compared with what, how well, for whom, in what settings, for what behaviours and why?’ The project involves an iterative process including: 1. Develop an ontology (structure for organising knowledge) of features of behaviour change intervention evaluations using a consensus process with international experts to, 2. Annotate published literature using the ontology, 3. Build an automated feature extraction system, 4. Build a Machine Learning and Reasoning system to synthesise the evidence, 5. Develop an interactive user interface to interrogate and update the knowledge system created. The project builds on taxonomies of behaviour change already developed, and existing ontologies (e.g. the Cochrane PICO ontology) and feature extraction systems (e.g. EPPI-Reviewer). It will focus initially on the use-case of smoking cessation but the project team will make available resources, products and findings throughout the life of the project to encourage collaboration.