EMOTIONALLY ADAPTIVE CYBER-THERAPIST USING GENERATIVE AI

The “Emotionally Adaptive Cyber-Therapist using Generative AI” successfully demonstrates the integration of emotion recognition and large language models to deliver personalized, empathetic conversational support. The system was implemented using a React.js frontend, Node.js backend, and LLM-based API integration, enabling dynamic mood detection and context-aware response generation. Experimental evaluation confirmed that the application can accurately interpret user input, classify emotional states such as anxiety or fatigue, and generate supportive, human-like responses that encourage reflection and emotional regulation. The architecture proved stable and responsive under normal operational conditions. Although API token limitations were encountered during extended response testing, these constraints were external and did not affect the core system design. Optimization techniques such as prompt refinement and token control improved efficiency and reliability. Overall, the project validates the feasibility of Generative AI in digital mental health support systems. With scalable infrastructure and enhanced emotional modelling, the system has strong potential for real-world deployment as an accessible AI-driven emotional companion.

1.               Russell, S., & Norvig, P. (2021). Artificial Intelligence: A Modern Approach. Pearson Education. 2.               Jurafsky, D., & Martin, J. H. (2020). Speech and Language Processing. Pearson. 3.               Vaswani, A. et al. (2017). “Attention is All You Need.” Advances in Neural Information Processing Systems (NeurIPS). 4.               Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep Learning. MIT Press. 5.               Devlin, J. et al. (2019). “BERT: Pretraining of Deep Bidirectional Transformers   for             Language Understanding.” NAACL-HLT. 6.               OpenAI (2023). “GPT-4 Technical Report.” OpenAI Research Papers. 7.               Picard, R. W. (1997). Affective Computing. MIT Press. 8.               Calvo, R. A., & D’Mello, S. (2010). “Affect Detection: An Interdisciplinary Review of Models, Methods, and Their Applications.” IEEE Transactions on Affective Computing. 9.               Miner, A.         S.,        et         al. (2016). “Smartphone-Based Conversational  Agents and Responses to Questions About Mental Health.” JAMA Internal Medicine.