Accepted for/Published in: Journal of Medical Internet Research
Date Submitted: Mar 28, 2025
Date Accepted: Jul 30, 2025
Assessing Heterogeneity in Sentiment Changes in Text-based Counselling: A Latent Class Trajectory Analysis
ABSTRACT
Background:
Online text-based counselling services are becoming increasingly popular. However, their text-based nature and anonymity pose challenges in tracking and understanding shifts in help-seekers’ emotional experience within a session. These characteristics make it difficult for service providers to tailor interventions to individual needs, potentially diminishing service effectiveness and user satisfaction.
Objective:
This study sought to identify distinct within-session sentiment trajectories among help-seekers in online text-based counselling and examine key predictors of trajectory membership.
Methods:
A total of 6,207 counselling sessions were randomly extracted from an online text-based counselling service in Hong Kong. A Latent Class Trajectory Analysis (LCTA) of help-seekers’ in-session sentiment was conducted using a Growth Mixture Model (GMM) to identify latent groups of help-seekers exhibiting specific sentiment trajectories. Sentiment scores of help-seeker messages, labelled by ChatGPT, served as the primary variable for trajectory modelling. Subsequently, a multinomial logistic regression was performed to identify variables associated with class membership.
Results:
The GMM identified three distinct sentiment trajectories as the best fit: i) Steady Improvement (18.9%), ii) Deterioration (18.0%), and iii) Dip-Then-Rebound (63.1%). Compared to the Dip-Then-Rebound Class, help-seekers in the Deterioration Class were more likely to report suicidal ideation, present with family or physical health-related concerns, have an unknown gender status, access the service through the anonymous channel, depart from the session prematurely, and have shorter session durations.
Conclusions:
We identified three distinct trajectories of help-seekers’ in-session sentiment. Identifying the most likely trajectory at an early stage in the session could potentially help counsellors adjust their approaches, thereby improving the effectiveness of text-based counselling and enhancing help-seeker satisfaction.
Citation
Request queued. Please wait while the file is being generated. It may take some time.
Copyright
© 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.