Thematic Analysis Using A Machine Learning Approach on User Reviews for Depression and Anxiety Chatbot Applications (Preprint)
BACKGROUND Anxiety and depression are amongst 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’ opinion and satisfaction of chatbot apps. 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 review comments. METHODS We analyzed 205,881 user review comments from chatbots dedicated 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 analysed the reviews using word frequencies of bigrams (words in pair).A topic modelling technique, Latent Dirichlet Allocation (LDA) was applied to identify topics in the reviews, and analysed for detecting themes and subthemes. RESULTS A thematic analysis was conducted on 5 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 appear to have the ability to provide users suffering from anxiety and depression feel confident and give them support via a tool that is easy to use, 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 appealing user interfaces.