The Human Behaviour-Change Project (HBCP) is creating an online ‘Knowledge System’ that uses Artificial Intelligence, in particular Natural Language Processing and Machine Learning, to extract information from intervention evaluation reports to answer key questions about the evidence. It is a collaboration between behavioural scientists, computer scientists and systems architects.
The Knowledge System will continually search publication databases to find behaviour change intervention evaluation reports, extract and synthesise the findings, provide up-to-date answers to questions, and draw inferences about behaviour change. Practitioners, policy makers and researchers will be able to query the system to obtain answers to variants of the key question: ‘What intervention(s) work, compared with what, how well, with what exposure, with what behaviours, for how long, for whom, in what settings and why?’
The project team is committed to open science and generating products and resources for the scientific community to use. These will be accessible via this website. There is strong engagement of the scientific community as the project evolves, with an International Advisory Board and peer review panels to comment on specific components.
Behavioural Scientists are developing an ‘ontology’ (The Behaviour Change Intervention Ontology – BCIO): a defined set of entities and their relationships. This will be used to organise information in a form that enables efficient accumulation of knowledge and enables links to other knowledge systems. They are also extracting information by hand to provide a reference set for the automated information extraction system.
Computer Scientists are developing algorithms to automatically extract information from published reports. This is being used to populate a database of research findings structured according to the Behaviour Change Intervention Ontology (BCIO). Machine Learning and reasoning algorithms are being developed to generate insights and answer queries from these data.
Systems Architects are developing user and machine interfaces for the Knowledge System. These will allow the system to be queried by practitioners, policy makers and researchers, and to interact with other automated systems.
Centre for Behaviour Change
University College London
1-19 Torrington Place, London, WC1E 7HB