EARLY MENTAL HEALTH RISK DETECTION USING ELECTRA

Read full text Summarise with VIRAT
Cited by: 0
References: 6

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

Mental health problems such as depression, anxiety, and suicidal ideation have become a major global concern.Early detection of mental health risks can help provide timely support and prevent severe psychological conditions.However, identifying mental health issues at an early stage is challenging because individuals often express their emotions indirectly through text on social media platforms, online forums, and digital communication channels.This paper proposes an Early Mental Health Risk Detection System using ELECTRA (Efficiently Learning an Encoder that Classifies Token Replacements Accurately).The system analyzes textual data to identify patterns related to emotional distress, negative thoughts, and psychological risk indicators.Natural Language Processing (NLP) techniques are used to preprocess text data, while the ELECTRA transformer model is used to classify mental health risk levels.The proposed system consists of several components including text preprocessing, feature extraction, ELECTRAbased classification, and risk prediction modules.The model is trained using labeled mental health datasets and evaluated using performance metrics such as accuracy, precision, recall, and F1-score.Experimental results demonstrate that the ELECTRA-based model provides improved efficiency and classification accuracy compared to traditional machine learning approaches.The proposed system can assist mental health professionals, researchers, and support organizations in identifying individuals at risk and providing early intervention strategies.

Fields of Study & Subjects

Mental Health via Writing Sentiment Analysis and Opinion Mining Emotion and Mood Recognition

Publication details

Journal / source
International Journal of Progressive Research in Engineering Management and Science
Publication date
28 March 2026
Language
EN