Mental health management system using LSTM model

View at publisher Summarise with VIRAT
Authors: Stella Joseph, P. Karthikeyan, Padmapriya Kondalsamy, Chandra Vanaraj, M. Arun Anoop, Saravanakumar Paramasivam
Cited by: 0
References: 16

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

In the modern era, individuals frequently encounter stress stemming from diverse sources like heavy workloads, financial strains, societal pressures, technological advancements, information overload, imbalance between work and personal life, and social unrest. These factors can induce feelings of overwhelm, uncertainty, and pressure, contributing to heightened stress levels. So, in today’s pervasive landscape of stress, there is a rising need for inventive stress management solutions. However, addressing the varying stressors experienced by individuals poses challenges. Therefore, evaluating their stress levels becomes imperative. This study presents a methodology for analyzing individual stress levels using deep learning models to offer tailored solutions. The proposed model leverages the Mental health Counselling Conversational Dataset alongside data gathered from doctor-recommended quiz questions to apply Natural Language Processing algorithms (NLP), including Long Short-Term Memory (LSTM), Adaptive Boosting (AdaBoost) and Random Forest (RF)models. LSTM demonstrates a testing accuracy of 99.56% when applied to real-time data. This study highlights the significance of stress management and the capability of deep learning to propose customized solutions, thereby safeguarding individuals’ well-being.

Fields of Study & Subjects

Mental Health via Writing Emotion and Mood Recognition Artificial Intelligence in Healthcare

Publication details

Journal / source
AIP conference proceedings
Volume
3341
Pages
020063–020063
Publication date
1 January 2026
Language
EN