Authors : Aadya Mishra; Charu Srivastav; Dr. Shalini Lamba; Rinku Raheja

Volume/Issue : Volume 11 - 2026, Issue 4 - April

---

Google Scholar : https://tinyurl.com/5bztf6rd

DOI : https://doi.org/10.38124/ijisrt/26apr839

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

---

Abstract : One of the biggest challenges nowadays is suicide and careful mental health care is urgently needed. The available models of emotion analysis are usually not reactive in real-time, not culturally adaptable and interpretable which reduces their effectiveness in suicide prevention via social media monitoring. This paper proposes a new Hybrid Adaptive Emotion Analysis Model (HAEAM) where the multimodal data are used: text, audio and visual combined with CNNs, BiLSTM with attention and weighted fusion to provide a better perception of detection of emotions in real-time. The model presents a context-sensitive adaptivity module of platform and cultural sensitivity and brings in Explainable AI (XAI) functions that guarantee transparency and ethical compliance.

Keywords : Suicide Prevention, Emotion Analysis, Real-Time Detection, Multimodal AI, Explainable AI.

References :

1. World Health Organization. (2023). Suicide Fact Sheet. WHO.
2. Weaver, C., et al. (2025). Global, regional, and national burden of suicide, 1990–2021. The Lancet Public Health.
3. Centers for Disease Control and Prevention. (2024). Suicide Data and Statistics (U.S.).
4. Patel, N., et al. (2022). Challenges in Mental Health Counseling Engagement. Frontiers in Psychiatry.
5. Kim, J., et al. (2021). Technology for Real-Time Detecting Emotional Distress. PMC.
6. Nguyen, T., et al. (2023). Limitations in Emotional Detection Models. Medical News Today.
7. Torres, M., et al. (2022). Real-Time Emotion Recognition and Crisis Intervention. Medical News Today.
8. Chen, L., et al. (2021). Cultural Context and Sarcasm in NLP Models. BMJ Quality & Safety, 33(10), 663.
9. Wang, Y., et al. (2023). Errors in Suicidal Thought Detection Models. International Association for Suicide Prevention.
10. Garcia, M., et al. (2024). Suicide Trends in Ecuador and Gender Differences. Our World in Data.
11. Lee, D., et al. (2022). Speech Emotion Recognition in Crisis Hotlines. Frontiers in Psychiatry.
12. Alghazzawi, D., et al. (2025). Explainable AI-based Suicidal and Non-Suicidal Ideations Detection Using Ensemble Techniques. Scientific Reports.
13. Kerz, E., Zanwar, S., Qiao, Y., & Wiechmann, D. (2023). Toward Explainable AI (XAI) for Mental Health Detection Based on Language Behavior. Frontiers in Psychiatry.
14. Atlam, E. S., et al. (2025). Explainable Artificial Intelligence Systems for Predicting Mental Health Disorders. ScienceDirect.
15. Ibrahimov, Y., Anwar, T., & Yuan, T. (2015). Explainable AI for Mental Disorder Detection via Social Media: A Survey and Outlook. arXiv.
16. Joyce, D. W., et al. (2023). Explainable Artificial Intelligence for Mental Health Through Social Media. PMC.
17. Aggarwal, L. (2025). Real-Time Image Processing and Smart Healthcare Using Deep Learning. ScienceDirect.
18. Zanwar, S., et al. (2025). AI-Based Mental Health Prediction from Social Media Using Hybrid Models. Journal of AI in Suicide Prevention.
19. Giuntini, F., et al. (2025). A Deep Learning-Based Hybrid Model for Depression Detection from Social Media. Journal of Advanced Information Technology, 103(12).