The Human Behaviour Change Project: Digitising the knowledge base on effectiveness of behaviour change interventions
-
1
University College London, United Kingdom
-
2
Aberdeen University, United Kingdom
-
3
IBM Research Dublin, Ireland
-
4
University of Cambridge, United Kingdom
Rationale
Intervention developers, researchers, policy-makers and practitioners need access to the best available evidence on what interventions work, compared with what, how well, for what behaviours, for whom, in what settings and why. Evidence about behaviour change interventions, including digital interventions, is currently being produced much more rapidly than humans can identify, read and process. It is also being reported in ways that limit our ability to synthesise it to draw generalisable conclusions. This limits advances in our understanding of behaviour change and our ability to design more effective interventions.
Aim
This presentation describes the initial phase of The Human Behaviour Change Project, which will harness the potential of digital technologies to advance our understanding of behaviour change. This first phase will develop an ‘ontology’ (a formal structure for organising knowledge in terms of defined constructs and their relationships) of behaviour change intervention (BCI) evaluations and develop a natural language processing (NLP) system to populate the ontology by automatically extracting and organising information from published research reports. These constitute part of a major project,
Methods: The project involves a collaboration of behavioural, computer and information scientists in an iterative process.
1. Behavioural and information scientists will lead on building an international consensus around an ontology of BCIs that captures, for each evaluation, information on: 1) interventions and comparators: features of content, delivery, and exposure, 2) behavioural targets: types of behaviour change and how they are operationalized, 3) context: features of study samples and settings, 4) putative mechanisms of action: proposed logic models of the interventions, 5) effect sizes, and 6) features of the evaluation needed for weighting and bias estimates.
2. Computer and information scientists will lead on building an NLP system to extract information from published research reports of BCI evaluations to populate and extend the ontology. This will draw on, and extend, technology developed by IBM Research to extract information from unstructured text in a variety of domains.
Outputs: This is intended to be an ongoing programme of work so that outputs will be continually generated and updated. The initial outputs will be: an international consortium of behavioural scientists engaged with the mission of building and using the BCI ontology, the first full version of a formal BCI ontology, an annotation tool to allow users to manually extract features of BCI evaluation reports to populate the ontology, an NLP system to automate as far as is practicable the process of feature extraction, and a populated ontology that can be searched and processed to access and synthesise key findings. This will provide the basis for the next phase, a Machine Learning system to synthesise evidence in the populated ontology to create knowledge about behaviour change; and an interface allowing users to interrogate and update the knowledge structure and evidence base.
Conclusions: This collaboration between behavioural, computer and information scientists has the potential to make a step-change in the accessibility and value of information about BCIs, and provide an important resource for digital intervention developers, researchers, policy-makers and practitioners.
Acknowledgements
Funded by the Wellcome Trust
Keywords:
Behaviour Change,
ontology,
Natural Language Processing,
Interventions,
Evidence synthesis
Conference:
3rd UCL Centre for Behaviour Change Digital Health Conference 2017: Harnessing digital technology for behaviour change, London, United Kingdom, 22 Feb - 23 Feb, 2017.
Presentation Type:
Research abstract
Topic:
Digital Health
Citation:
Michie
S,
West
R,
Johnston
M,
Mac Aonghusa
P,
Thomas
J,
Kelly
M and
Shawe-Taylor
J
(2017). The Human Behaviour Change Project: Digitising the knowledge base on effectiveness of behaviour change interventions.
Front. Public Health.
Conference Abstract:
3rd UCL Centre for Behaviour Change Digital Health Conference 2017: Harnessing digital technology for behaviour change.
doi: 10.3389/conf.FPUBH.2017.03.00008
Copyright:
The abstracts in this collection have not been subject to any Frontiers peer review or checks, and are not endorsed by Frontiers.
They are made available through the Frontiers publishing platform as a service to conference organizers and presenters.
The copyright in the individual abstracts is owned by the author of each abstract or his/her employer unless otherwise stated.
Each abstract, as well as the collection of abstracts, are published under a Creative Commons CC-BY 4.0 (attribution) licence (https://creativecommons.org/licenses/by/4.0/) and may thus be reproduced, translated, adapted and be the subject of derivative works provided the authors and Frontiers are attributed.
For Frontiers’ terms and conditions please see https://www.frontiersin.org/legal/terms-and-conditions.
Received:
22 Feb 2017;
Published Online:
22 Feb 2017.
*
Correspondence:
Prof. Susan Michie, University College London, London, United Kingdom, s.michie@ucl.ac.uk