Smartwatch-Based Tailored Gamification and User Modeling for Motivating Physical Exercise: Experimental Study With the Maximum Difference Scaling Segmentation Method
Bibliographic record
Abstract
BACKGROUND: Smartwatch-based gamification holds great promise for enhancing fitness apps and promoting physical exercise; however, empirical evidence on its effectiveness remains inconclusive, partly due to "one-size-fits-all" design approaches that overlook individual differences. While the emerging research area of tailored gamification calls for more accurate user modeling and better customization of game elements, existing studies have relied primarily on rating scale-based measures and correlational analyses with methodological limitations. OBJECTIVE: This study aimed to improve smartwatch-based gamification through an innovative user modeling approach 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 used the maximum difference scaling (MaxDiff) technique, which can overcome the limitations of traditional methods. METHODS: With data collected from 2 MaxDiff experiments involving 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 identified. Prediction models were also proposed for quickly classifying future users into the right segments to provide them with tailored gamification solutions on smartwatch fitness apps. RESULTS: We identified 3 segments of smartwatch users based on their preferences for gamification. More importantly, we uncovered 4 segments motivated by goals, immersive experiences, rewards, or social comparison. 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 2 sets of user segments (ie, those based on preferences for game elements vs those based on the motivational effects of the elements), indicating the gap between what people enjoy using on smartwatches and what can motivate them for physical exercise engagement. CONCLUSIONS: To our knowledge, this study is the first to investigate MaxDiff-based user segmentation for tailored gamification on smartwatches promoting physical exercise and contributes to a detailed understanding of preferences for, and the effectiveness of, different game elements among different groups of smartwatch users. As existing tailored gamification studies continue to explore ways of user modeling with mostly surveys and questionnaires, this study 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.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".