Computer-delivered interventions for reducing alcohol consumption: meta-analysis and meta-regression using behaviour change techniques and theory

Abstract

The current aim was to examine the effectiveness of behaviour change techniques (BCTs), theory and other characteristics in increasing the effectiveness of computer-delivered interventions (CDIs) to reduce alcohol consumption. Included were randomised studies with a primary aim of reducing alcohol consumption, which compared self-directed CDIs to assessment-only control groups. CDIs were coded for the use of 42 BCTs from an alcohol-specific taxonomy, the use of theory according to a theory coding scheme and general characteristics such as length of the CDI. Effectiveness of CDIs was assessed using random-effects meta-analysis and the association between the moderators and effect size was assessed using univariate and multivariate meta-regression. Ninety-three CDIs were included in at least one analysis and produced small, significant effects on five outcomes (d₊ = 0.07–0.15). Larger effects occurred with some personal contact, provision of normative information or feedback on performance, prompting commitment or goal review, the social norms approach and in samples with more women. Smaller effects occurred when information on the consequences of alcohol consumption was provided. These findings can be used to inform both intervention- and theory-development. Intervention developers should focus on, including specific, effective techniques, rather than many techniques or more-elaborate approaches.

KEYWORDS:

• Alcohol
• computer
• intervention
• behaviour change techniques
• theory
• meta-analysis

Acknowledgements

The authors gratefully acknowledge Dan Costa for his statistical advice and Amelia Scott for her assistance with second-coding moderators.

Disclosure statement

No potential conflict of interest was reported by the authors.

ORCID

Nicola Black http://orcid.org/000-0002-7933-4833

Barbara Mullan http://orcid.org/0000-0002-0177-8899

Notes

1. Asterisks indicate truncation. For example, drink* would yield results for drink, drinker, drinking, etc.

2. Four of the five contacted authors responded and provided data for five of the seven CDIs. The remaining two CDIs were still included in at least one meta-analysis, due to available data for other outcomes.

3. For those interested, BCT31 has previously been assessed via meta-analysis (McCambridge & Kypri, 2011).

4. Though, some BCTs might be difficult to adapt to this medium (e.g., BCT37: using reflective listening).