Paper Type
ERF
Abstract
AI driven diabetes apps offer potential for users with chronic diseases to better manage their health. However, such apps largely offer generic non-tailored information and have high rates of attrition. This work shows initial results in a project creating a theory-informed recommender app for diabetes management. Using the Functional Theory of Attitude and the Cognitive Experiential Self Theory this paper posits that recommender apps that present information fitting a user’s cognitive style will encourage greater adherence to the recommendations made and shows how generative AI can support this task. The contribution of the work is in demonstrating how intelligent technologies can operationalize the use of these theories, establishing a scalable process for testing and applying these theories in the recommender app context. The work proposes how generative AI can be used to support the design and tailoring of such apps to produce more effective tools to support personal health.
Paper Number
1867
Recommended Citation
Delir Haghighi, Pari; Lederman, Reeva; and Dreyfus, Suelette, "A Theory-Driven Approach to Behaviour Change in Diabetes Recommender Apps" (2025). AMCIS 2025 Proceedings. 32.
https://aisel.aisnet.org/amcis2025/intelfuture/intelfuture/32
A Theory-Driven Approach to Behaviour Change in Diabetes Recommender Apps
AI driven diabetes apps offer potential for users with chronic diseases to better manage their health. However, such apps largely offer generic non-tailored information and have high rates of attrition. This work shows initial results in a project creating a theory-informed recommender app for diabetes management. Using the Functional Theory of Attitude and the Cognitive Experiential Self Theory this paper posits that recommender apps that present information fitting a user’s cognitive style will encourage greater adherence to the recommendations made and shows how generative AI can support this task. The contribution of the work is in demonstrating how intelligent technologies can operationalize the use of these theories, establishing a scalable process for testing and applying these theories in the recommender app context. The work proposes how generative AI can be used to support the design and tailoring of such apps to produce more effective tools to support personal health.
When commenting on articles, please be friendly, welcoming, respectful and abide by the AIS eLibrary Discussion Thread Code of Conduct posted here.
Comments
IntelFuture