Analyzing User Usage Patterns and Adherence in Mental Health Mobile Applications Using Simulated Data (Preprint)

Author:

Wu Liu,Dong Yu-Ting,Sun Xiao-Xiang,Jiang Ze-fei,Liu Guang,Zhang Hong

Abstract

BACKGROUND

Mental health disorders are increasingly prevalent globally, leading to a growing reliance on digital health interventions, particularly mental health mobile applications. These apps provide accessible mental health support but their effectiveness largely depends on user engagement and adherence.

OBJECTIVE

This study aims to analyze user usage patterns and adherence in mental health mobile applications using simulated data to identify key factors influencing user engagement and adherence.

METHODS

We generated a robust simulated dataset representing real-world usage scenarios, including variables such as weekly session counts, average session durations, and features used. The K-means clustering algorithm was employed to categorize users into three distinct clusters based on their engagement levels. Statistical analyses were conducted to examine the distribution of session counts, session durations, and feature usage.

RESULTS

The analysis identified three user clusters: low engagement, moderate engagement, and high engagement. Most users engaged with the app on a near-daily basis, with sessions averaging around 20 minutes. Meditation was the most frequently used feature, followed by courses and mood tracking. These findings highlight the diverse engagement levels among users and the importance of tailoring app features to different user needs.

CONCLUSIONS

Understanding user behavior through simulated data provides valuable insights for optimizing mental health app design. By integrating personalized feedback and tailoring features to meet user preferences, developers can enhance user adherence and engagement. Future research should validate these findings with real-world data and leverage advanced analytics to further refine digital mental health interventions.

Publisher

JMIR Publications Inc.

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3