Abstract

The growing interest in wearable devices has stimulated the development of mHealth applications: users can be monitored at different levels of granularity and their data can be exploited for recommendations about different aspects of their conditions, i.e. physical, psychological and social. To this aim, recommendation systems should be able to profile patients in order to suggest them the most proper actions to promote effective behavior changes. This paper presents a solution to this challenging research topic implemented in an Android app, based on the adoption of fuzzy logic to cluster users according to quantitative and qualitative variables about their physical and psychological well-being. Four classes have been obtained from the two models developed, in accordance with previous experiments. The final aim of user profiling is promoting group physical activity among users characterized by similar behaviors.

Recommended Citation

Sartori, F. & Tonelli, L. (2021). Fuzzy Personalization of Mobile Apps: A Case Study from mHealth Domain. In E. Insfran, F. González, S. Abrahão, M. Fernández, C. Barry, H. Linger, M. Lang, & C. Schneider (Eds.), Information Systems Development: Crossing Boundaries between Development and Operations (DevOps) in Information Systems (ISD2021 Proceedings). Valencia, Spain: Universitat Politècnica de València.

Paper Type

Full Paper

Share

COinS
 

Fuzzy Personalization of Mobile Apps: A Case Study from mHealth Domain

The growing interest in wearable devices has stimulated the development of mHealth applications: users can be monitored at different levels of granularity and their data can be exploited for recommendations about different aspects of their conditions, i.e. physical, psychological and social. To this aim, recommendation systems should be able to profile patients in order to suggest them the most proper actions to promote effective behavior changes. This paper presents a solution to this challenging research topic implemented in an Android app, based on the adoption of fuzzy logic to cluster users according to quantitative and qualitative variables about their physical and psychological well-being. Four classes have been obtained from the two models developed, in accordance with previous experiments. The final aim of user profiling is promoting group physical activity among users characterized by similar behaviors.