Smartwatch-Based Tailored Gamification and User Modeling for Motivating Physical Exercise: A MaxDiff Segmentation Approach.

Abstract

Background: Smartwatch-based gamification holds great promise for empowering fitness applications and promoting physical exercise, yet existing empirical evidence on its effectiveness remains inconclusive, partly due to "one-size-fits-all" design approaches neglecting individual differences. While the emerging research area of tailored gamification calls for more accurate user modeling and better customization of game elements, existing studies relied primarily on rating-scale-based measures and correlational analyses with methodological limitations.

Objective: This study aimed to improve smartwatch-based gamification with an innovative approach of user modeling, in order to better motivate physical exercise among different user groups with tailored solutions. It incorporated both individual preferences and needs for game elements into the user segmentation process, and employed the Maximum Difference Scaling (MaxDiff) technique that can alleviate the limitations of traditional methods.

Methods: With data collected from two MaxDiff experiments on 378 smartwatch users and Latent Class statistical models, the relative power of each of the 16 popular game elements was examined in terms of what users liked and what motivated them to exercise, based on which distinct user segments were discovered. Prediction models were also proposed for quickly classifying future users into the right segments, in order to provide them with tailored gamification solutions on smartwatch fitness applications.

Results: We discovered three segments of smartwatch users based on their preferences for gamification, and more important, four segments motivated by goals, immersive experiences, rewards or social comparison respectively. Such user heterogeneity confirmed the susceptibility of the effects of gamification, and indicated the necessity of accurately matching gamified solutions with user characteristics to better change health behaviors through different mechanisms for different targets. Important differences were also observed between the two sets of user segments (i.e., whether based on preferences for or motivational effects of game elements), indicating the gap between what people enjoy using on smartwatches and what can motivate them for physical exercise engagement.

Conclusions: As far as we know, this study was the first investigation of MaxDiff-based user segmentation for tailored gamification on smartwatches promoting physical exercise, and contributed to a detailed understanding about preferences for and effectiveness of different game elements among different groups of smartwatch users. As existing tailored gamification studies were still exploring ways of user modeling with mostly surveys and questionnaires, this study also supported the adoption of MaxDiff experiments as an alternative method, to better capture user heterogeneity in the health domain and inform the design of tailored solutions for more application types beyond smartphones.

Clinicaltrial: