Mmbayi, Ian IgadoGakii, ConsolataMusyoka, Faith Mueni2026-02-152026-02-152025Mmbayi, I. I., Gakii, C., & Musyoka, F. M. (2025). Sentiment Analysis‐Based Model for Monitoring User Engagement With Mental Health Chatbots. Engineering Reports, 7(6), e70247.http://repository.embuni.ac.ke/handle/123456789/4579Mental health challenges, particularly among youth, are compounded by stigma and limited access to professional care. Thishas driven demand for scalable digital solutions like chatbots. This study introduces a sentiment analysis-based model toassess user satisfaction with mental health chatbots, analyzing 82 102 reviews from six popular apps on Google Play andApple’s App Stores. A multi-class sentiment classification of positive, negative, and neutral was implemented, enhanced bySynthetic Minority Over-sampling Technique for class balancing, comparing five traditional machine learning models with Bidi-rectional Encoder Representations from Transformers, a transformer model. Random Forest achieved 98.18% accuracy amongtraditional models, while BERT outperformed all with 99.17% accuracy, surpassing prior benchmarks. Aspect-based analysisrevealed that Emotion and Usability drive positive feedback, while Reliability issues fuel negative sentiments, offering action-able insights for developers to enhance chatbot design. This work advances digital mental health research by integratingmulti-class classification, transformer models, and aspect-based analysis, demonstrating a scalable framework for evaluating userfeedback.enaspect-based analysis | BERT | chatbots | machine learning | mental health | sentiment analysis | SMOTE | user reviewsArticle