Fitness-Based Recommender Systems for Reducing Sedentary Behaviour

Abstract

Obesity and sedentary behaviour represent one of the greatest global challenges to good health and wellbeing. The goal of the thesis is to promote physical activity among young adults by comparing the effectiveness of content-based and context-aware recommender systems on perceived post-intervention user experience, exercise motivation, and projected behaviour performance. Gender differences are explored. A 73-person user study compares recommender systems that solely focus on generating fitness plans (control group) against alternatives that incorporate psychosocial frameworks and explainability into the generation process (experimental group). The context-aware recommender systems provided the highest level of perceived post-intervention user experience, exercise motivation, and projected behaviour performance compared to the content-based recommender systems. Among females, the experimental group which leveraged persuasive design techniques showed numerical gains in exercise motivation and projected behaviour performance compared to the control group, however, the interaction effect was non-significant. Future work should investigate hybrid recommender systems in generating personalized exercise recommendations.