Skip to main content
padlock icon - secure page this page is secure

Investigation of Influential Factors of Predicting Individuals' Use and Non-use of Fitness and Diet Apps on Smartphones: Application of the Machine Learning Algorithm (XGBoost)

Buy Article:

$39.00 + tax (Refund Policy)

Objectives: In this study, we aimed to find the influential factors in determining individuals' use and non-use of fitness and diet apps on smartphones. To this end, we focused on diverse groups of predictors that would significantly affect people's use and non-use of these apps. Methods: Overall, we considered 105 factors as potential predictors and included them in further analyses using a machine learning algorithm, XGBoost. The main reason for selecting this particular algorithm was that it had been known as one of the most accurate and popular algorithms for predicting consumer behaviors. Results: We found the accuracy score of those factors for predicting people's use and non-use of fitness and diet apps was approximately 71.3%. In particular, the most influential predictors were mainly related to social influence, media use, overeating, social support, health management, and attitudes toward exercise. Conclusion: These findings contribute to helping scholars and practitioners to develop more practical strategies of the implementation of fitness and diet apps.
No Reference information available - sign in for access.
No Citation information available - sign in for access.
No Supplementary Data.
No Article Media
No Metrics

Keywords: FITNESS AND DIET APPS; MACHINE LEARNING ALGORITHM; SOCIAL INFLUENCE; XGBOOST; mHEALTH

Document Type: Research Article

Affiliations: 1: Jaehee Cho, Associate Professor, School of Media, Arts & Science, Sogang University, Seoul, South Korea;, Email: [email protected] 2: Sehwan Kim, Associate Professor, Department of Biomedical Engineering, Dankook University, Cheonan, South Korea 3: Gwangjin Jeong, MA student, Department of Biomedical Engineering, Dankook University, Cheonan, South Korea 4: Chonghye Kim, Doctoral student, School of Mass Communication, Sogang University, Seoul, South Korea 5: Ja-Kyoung Seo, MA student, School of Mass Communication, Sogang University, Seoul, South Korea

Publication date: January 1, 2021

More about this publication?
  • The American Journal of Health Behavior seeks to improve the quality of life through multidisciplinary health efforts in fostering a better understanding of the multidimensional nature of both individuals and social systems as they relate to health behaviors.

    The Journal aims to provide a comprehensive understanding of the impact of personal attributes, personality characteristics, behavior patterns, social structure, and processes on health maintenance, health restoration, and health improvement; to disseminate knowledge of holistic, multidisciplinary approaches to designing and implementing effective health programs; and to showcase health behavior analysis skills that have been proven to affect health improvement and recovery.

  • Editorial Board
  • Information for Authors
  • Submit a Paper
  • Subscribe to this Title
  • Review Board
  • Reprints and Permissions
  • Ingenta Connect is not responsible for the content or availability of external websites
  • Access Key
  • Free content
  • Partial Free content
  • New content
  • Open access content
  • Partial Open access content
  • Subscribed content
  • Partial Subscribed content
  • Free trial content
Cookie Policy
X
Cookie Policy
Ingenta Connect website makes use of cookies so as to keep track of data that you have filled in. I am Happy with this Find out more