Location
Hilton Hawaiian Village, Honolulu, Hawaii
Event Website
https://hicss.hawaii.edu/
Start Date
3-1-2024 12:00 AM
End Date
6-1-2024 12:00 AM
Description
In this paper, we present a novel adaptive system architecture for positive health behavior change. Leveraging an advanced large language model as a knowledgebase, the system automatically generates personalized behavior change plans based on individual needs. It utilizes established health behavior change theories to provide timely, context-specific interventions and nudges. We outline the system’s key components and functionality, demonstrating its adaptability through a structured walkthrough of ”Achieve healthy weight” and ”Manage Job-Related Stress” scenarios. We demonstrate that system dynamically adapts its recommendations based on users’ evolving behaviors, intentions, circumstances, and stage in the behavior change process, ensuring ongoing relevance and effectiveness. The paper highlights the potential of a large language model to serve as a knowledge base in health behavior change support systems.
Recommended Citation
Bhavsar, Maitry and Patel, Sachin, "Adaptive System Architecture for Health Behavior Change: Harnessing the Power of Large Language Models" (2024). Hawaii International Conference on System Sciences 2024 (HICSS-57). 5.
https://aisel.aisnet.org/hicss-57/hc/behavior_change/5
Adaptive System Architecture for Health Behavior Change: Harnessing the Power of Large Language Models
Hilton Hawaiian Village, Honolulu, Hawaii
In this paper, we present a novel adaptive system architecture for positive health behavior change. Leveraging an advanced large language model as a knowledgebase, the system automatically generates personalized behavior change plans based on individual needs. It utilizes established health behavior change theories to provide timely, context-specific interventions and nudges. We outline the system’s key components and functionality, demonstrating its adaptability through a structured walkthrough of ”Achieve healthy weight” and ”Manage Job-Related Stress” scenarios. We demonstrate that system dynamically adapts its recommendations based on users’ evolving behaviors, intentions, circumstances, and stage in the behavior change process, ensuring ongoing relevance and effectiveness. The paper highlights the potential of a large language model to serve as a knowledge base in health behavior change support systems.
https://aisel.aisnet.org/hicss-57/hc/behavior_change/5