Abstract
Autonomous e-coaching systems have the potential to improve people's health behaviors on a large scale. The intelligent behavior change support system eMate exploits a model of the human agent to support individuals in adopting a healthy lifestyle. The system attempts to identify the causes of a person's non-adherence by reasoning over a computational model (COMBI) that is based on established psychological theories of behavior change. The present work presents an extensive, monthlong empirical validation study (N=82) of eMate in which participants were coached in their everyday life -- using a mobile app and a website -- towards taking the stairs more often. The eMate reasoning mechanism is evaluated on its accuracy and its ability to promote behavior change. Results show that eMate (i) identifies and accurately targets the problematic constructs for an individual and (ii) positively affects aspects of behavior change through tailored interventions.
| Original language | English |
|---|---|
| Title of host publication | Proceedings of the 13th International Conference on Autonomous Agents and Multiagent Systems |
| Place of Publication | Paris, France |
| Publisher | International Foundation for Autonomous Agents and Multiagent Systems |
| Pages | 725-732 |
| Number of pages | 8 |
| ISBN (Electronic) | 9781634391313 |
| ISBN (Print) | 978-1-4503-2738-1 |
| Publication status | Published - 2014 |
| Event | 13th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2014 - Paris, France Duration: 5 May 2014 → 9 May 2014 |
Conference
| Conference | 13th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2014 |
|---|---|
| Country/Territory | France |
| City | Paris |
| Period | 5/05/14 → 9/05/14 |
Keywords
- Behavior change
- Decision support system
- E-coaching
- EHealth
- HCI
- Model-based diagnostics