Integrating counseling with technology: An evaluation of the Bicarakan.id application through user review analysis with machine learning

Online counseling has transformed mental health services by offering a convenient and cost-effective alternative to traditional in-person therapy. This study investigates the role of technology in counseling by analyzing user reviews of the Bicarakan.id app from the Google Play Store. A machine learning approach was employed to identify critical patterns and themes within the reviews. Text pre-processing methods such as tokenization, stop-word removal, and TF-IDF vectorization were applied to a dataset of 125 user reviews. The Elbow method helped determine the optimal number of clusters, which was three. Clustering performance was assessed using the Silhouette score, with three clusters yielding the highest average score of 0.4939, indicating a moderate level of clustering effectiveness. Cluster 1 primarily contained positive reviews, emphasizing user satisfaction with the app's services. Cluster 2 included more specific feedback on users' experiences with counselors and app features. Cluster 3 focused on the app's accessibility and ease of use while raising concerns about data privacy and the lack of offline consultation options. The study underscores the significance of using user feedback to enhance and improve technology-driven mental health solutions.