• ABHISHEK TIWARI
• ABIR ARORA
• AMIT KUMAR TRIPATHI
• ARYAN VERMA

Abstract: Mental health issues such as stress, anxiety, and depression are increasingly common among students, yet access to timely support remains limited. This paper presents a Student Mental Wellness Chatbot that provides emotional support and self-assessment through AI-driven emotion detection and CBT-based interventions. The chatbot integrates a BiLSTM model for emotion classification and a MiniLM SentenceTransformer for contextual understanding, functioning as a lightweight LLM. It also employs VADER sentiment analysis, crisis detection, and bilingual (English–Hindi) interaction via Argos Translate. Experimental evaluation demonstrates that the BiLSTM model achieved an accuracy of 92% on the dair-ai/emotion dataset, effectively identifying six key emotions — joy, sadness, anger, fear, love, and surprise. The chatbot successfully generated context-aware, empathetic, and student-specific responses, while maintaining offline functionality and data privacy. Future work aims to enhance personalization, integrate voice-based interaction, and fine-tune the model for real-time institutional deployment.

Mental Health, Emotion Detection, Machine Learning, BiLSTM, MiniLM, Natural Language Processing, CBT, PHQ-9, GAD-7, Sentiment Analysis, Crisis Detection, Multilingual Translation,Argos Translate, Student Wellbeing.

"MENTAL HEALTH SUPPORT TO STUDENTS USING NLP AND MACHINE LEARNING", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 12, page no.b196-b206, December-2025, Available :http://www.jetir.org/papers/JETIR2512129.pdf

"MENTAL HEALTH SUPPORT TO STUDENTS USING NLP AND MACHINE LEARNING", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 12, page no. ppb196-b206, December-2025, Available at : http://www.jetir.org/papers/JETIR2512129.pdf