Maintenance Notice

Due to necessary scheduled maintenance, the JMIR Publications website will be unavailable from Wednesday, July 01, 2020 at 8:00 PM to 10:00 PM EST. We apologize in advance for any inconvenience this may cause you.

Who will be affected?

Accepted for/Published in: Journal of Medical Internet Research

Date Submitted: Jul 18, 2023
Date Accepted: Apr 12, 2024

The final, peer-reviewed published version of this preprint can be found here:

Tracking and Profiling Repeated Users Over Time in Text-Based Counseling: Longitudinal Observational Study With Hierarchical Clustering

Xu Y, Chan CS, Chan E, Chen J, Cheung F, Xu Z, Liu J, Yip PS

Tracking and Profiling Repeated Users Over Time in Text-Based Counseling: Longitudinal Observational Study With Hierarchical Clustering

J Med Internet Res 2024;26:e50976

DOI: 10.2196/50976

PMID: 38815258

PMCID: 11176871

Tracking and Profiling Repeated Users Over Time in Text-based Counseling: A Longitudinal Observational Study with Hierarchical Clustering

  • Yucan Xu; 
  • Christian S. Chan; 
  • Evangeline Chan; 
  • Junyou Chen; 
  • Florence Cheung; 
  • Zhongzhi Xu; 
  • Joyce Liu; 
  • Paul S.F. Yip

ABSTRACT

Background:

Due to their accessibility and anonymity, online counseling services is expanding at an unprecedented rate. One of the most prominent challenges for such services is repeated users, who represent a small fraction of total users but consume significant resources by continuously returning the system with the same narrative and issues. A deeper understanding of repeated user and tailoring interventions may help improve service efficiency and effectiveness. Previous studies on repeated users were mainly on telephone counseling, and the classification of repeated users was arbitrary and failed to capture the diversity in this group of users.

Objective:

In this study, we aimed to develop a method that helps services derive systematic ways to profile repeated users in order to help improve the provision of interventions to different types of users and service effectiveness.

Methods:

We extracted session data from 29,400 users from a free, 24/7 online counseling service from 2018 to 2021. Hierarchical clustering was used to identify heterogeneity and classify repeated users based on users’ service utilization behaviors and characteristics. Further analyses were conducted between identified user groups to investigate factors associated with their revisiting and dependent behaviors.

Results:

Three clusters of repeated users with clear psychological profiles have been detected, including episodic, periodic, and dependent users. Repeated users showed a higher suicide risk and complex backgrounds than one-time users (p < .001). Higher risks, more severe help-seeking issues and willingness to use non-anonymous platforms were associated with higher service dependency (p < .001).

Conclusions:

This study provides a systematic way to identify and classify repeated users in online counseling services, which can facilitate frontline personnel in delivering efficient interventions. The findings and proposed method can be meaningful to the wider context of services in better service provision, resource allocation, and service effectiveness.


 Citation

Please cite as:

Xu Y, Chan CS, Chan E, Chen J, Cheung F, Xu Z, Liu J, Yip PS

Tracking and Profiling Repeated Users Over Time in Text-Based Counseling: Longitudinal Observational Study With Hierarchical Clustering

J Med Internet Res 2024;26:e50976

DOI: 10.2196/50976

PMID: 38815258

PMCID: 11176871

Download PDF


Request queued. Please wait while the file is being generated. It may take some time.

© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.