Accepted for/Published in: JMIR Formative Research
Date Submitted: Feb 1, 2021
Date Accepted: Dec 15, 2021
Thematic Analysis Using A Machine Learning Approach on User Reviews for Depression and Anxiety Chatbot Applications
ABSTRACT
Background:
Anxiety and depression are among the most commonly prevalent mental health disorders (CMDs) worldwide. Chatbot apps can play an important role in relieving anxiety and depression. Users’ reviews of chatbot apps are considered an important source of data to explore users’ opinions and satisfaction.
Objective:
This study aims to explore users’ opinions, satisfaction, and attitudes about anxiety and depression chatbot apps through conducting a thematic analysis of users’ reviews of 11 anxiety and depression chatbot apps collected from Google play and Apple store. In addition, we propose a workflow to provide a methodological approach for future analysis of apps review comments.
Methods:
We analyzed 205,581 user review comments from chatbots designed for users with anxiety and depression symptoms. Using scrapper tools, Google Play Scraper and App Store Scraper python libraries, we extracted text and metadata. The reviews were divided into positive and negative meta-themes, based on users’ rating per review. We analyzed the reviews using word frequencies of bigrams, words in pairs. A topic modelling technique, Latent Dirichlet Allocation (LDA) was applied to identify topics in the reviews, and analyzed for detecting themes and subthemes.
Results:
A thematic analysis was conducted on five topics for each sentimental set. Reviews were categorized as either positive or negative. For positive reviews, the main themes were confidence and affirmation building, adequate analysis, and consultation, caring as a friend, and easy to use. Whereas for negative reviews results revealed the following themes: usability issues, update issues, privacy and non-creative conversation.
Conclusions:
Chatbots can provide users, who suffer from anxiety and depression, with confidence and give them support via tools that are easy to use, of low cost, containing adequate symptom detection whilst providing feeling of having a close friend to converse with. Users tend to dislike technical and privacy issues. Users expect engaging and creative conversations via more appealing user interfaces.
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.