Proceedings of the International Conference on Intelligent Systems for a Sustainable Future (ISSF 2026)

<Previous Article In Volume
Next Article In Volume>

AI-Powered Mental Health Companion for Emotional Support and Self-Care Guidance

Authors
T. Kalpanashree1, M. Karthikayini1, R. Rajalakshmi1, *
1Department of Computer Science and Engineering, Sathyabama Institute of Science and Technology, Chennai, India
*Corresponding author. Email: rajalakshmi.cse@sathyabama.ac.in
Corresponding Author
R. Rajalakshmi
Available Online 16 June 2026.
DOI
10.2991/978-94-6239-693-7_19How to use a DOI?
Keywords
Mental Health AI; Multimodal Emotion Recognition; Sentiment Analysis; Stress Detection; Conversational Agents; Affective Computing; Self-Care Systems
Abstract

The problem of mental health becomes more widespread in the world, whereas the possibility to receive timely and stigma-free help is minimal. This research will help to satisfy the demand of a convenient and smart system of mental health assistance by designing the role of AI-based companion that would monitor emotions 24/7 and provide personalized tips on how to take care of oneself. The suggested system incorporates multimodal affective analysis, as it unites sentiment analysis of text based on VADER, stress classification based on decision tree models supplemented by LSTM and BiLSTM networks, visual emotional recognition via facial, and vocal emotion recognition based on speech to text analysis. A small TinyLLaMA chatbot provides sensitive and context- sensitive conversations based on the emotional condition of the user. Being a Flask-based web application, the platform allows tracking mood in real-time, adaptive support in conversations, and tailored coping suggestions. The main contribution of the work is that it consists of a unified multimodal representation and a computationally feasible design, which may be successfully applied to the real world. Through experimental assessment, there have been evidences of greater emotional awareness and effective stress monitoring and meaningful user interaction, which show how the system could serve as an aiding non-invasive mental health companion.

Copyright
© 2026 The Author(s)
Open Access
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

<Previous Article In Volume
Next Article In Volume>
Volume Title
Proceedings of the International Conference on Intelligent Systems for a Sustainable Future (ISSF 2026)
Series
Atlantis Highlights in Intelligent Systems
Publication Date
16 June 2026
ISBN
978-94-6239-693-7
ISSN
2589-4919
DOI
10.2991/978-94-6239-693-7_19How to use a DOI?
Copyright
© 2026 The Author(s)
Open Access
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Cite this article

risenwbib
TY  - CONF
AU  - T. Kalpanashree
AU  - M. Karthikayini
AU  - R. Rajalakshmi
PY  - 2026
DA  - 2026/06/16
TI  - AI-Powered Mental Health Companion for Emotional Support and Self-Care Guidance
BT  - Proceedings of the International Conference on Intelligent Systems for a Sustainable Future (ISSF 2026)
PB  - Atlantis Press
SP  - 170
EP  - 184
SN  - 2589-4919
UR  - https://doi.org/10.2991/978-94-6239-693-7_19
DO  - 10.2991/978-94-6239-693-7_19
ID  - Kalpanashree2026
ER  -