Identifying Behavior Change Techniques in an Artificial Intelligence-Based Fitness App: A Content Analysis
Health Education & Behavior · 2024
DOI: 10.1177/10901981231213586 ↗Kurz gefasst
Fachartikel in der Zeitschrift Health Education & Behavior, 2024. Verfasst von Hakan Kuru. Beteiligte Einrichtung: İstanbul Rumeli University, İstanbul, Turkey. Hauptthemen laut MEDLINE: Mobile Applications, Artificial Intelligence, Exercise, Health Promotion. Die Arbeit wurde bisher 16-mal zitiert (Crossref) und nennt 60 Literaturangaben.
Abstract (Originalsprache)
In the field of artificial intelligence-based fitness apps, the effective integration of behavior change techniques (BCTs) is critical for promoting physical activity and improving health outcomes. However, the specific BCTs employed by apps and their impact on user engagement and behavior change are not explored sufficiently. This study investigates the Freeletics fitness app through a mixed-methods approach to evaluate the use of BCTs. In the quantitative analysis, fifteen unique BCTs were identified based on the Behavior Change Technique Taxonomy (V1). In the qualitative analysis, user reviews ( n =400) were examined to understand perspectives on the app’s effectiveness in promoting behavior change. Goal setting, action planning, self-monitoring of behavior, and social support were among the most prevalent BCTs identified in the Freeletics app, and their effectiveness in enhancing user engagement and promoting behavior change was also highlighted by user reviews. Among the areas of improvement identified in the study were the need for simplifying personalization options and addressing user concerns regarding the specificity of feedback. The study underscores the importance of integrating BCTs effectively within AI-based fitness apps to drive user engagement and facilitate behavior change. It contributes valuable insights into the design and implementation of BCTs in fitness apps and offers recommendations for developers, emphasizing the significance of goal setting, feedback mechanisms, self-monitoring, and social support. By understanding the impact of specific BCTs on user behavior and addressing user concerns, developers can create more effective fitness apps, ultimately promoting healthier lifestyles and positive behavior change.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- İstanbul Rumeli University, İstanbul, Turkey.
- Middle East Technical University, Ankara, Turkey.
ORCID-Profile: Hakan Kuru
Zitieren
APA
Kuru, H. (2024). Identifying Behavior Change Techniques in an Artificial Intelligence-Based Fitness App: A Content Analysis. Health Education & Behavior. https://doi.org/10.1177/10901981231213586
Vancouver
Kuru H. Identifying Behavior Change Techniques in an Artificial Intelligence-Based Fitness App: A Content Analysis. Health Education & Behavior. 2024. doi:10.1177/10901981231213586
BibTeX
@article{Kuru2024,
author = {Kuru, Hakan},
title = {Identifying Behavior Change Techniques in an Artificial Intelligence-Based Fitness App: A Content Analysis},
journal = {Health Education & Behavior},
year = {2024},
doi = {10.1177/10901981231213586}
}
EUVIMED