A TRANSFORMER-BASED EXPLAINABLE AI FRAMEWORK FOR EARLY DETECTION AND MITIGATION OF LONELINESS USING SENTIMENT AND CONTEXTUAL MODELLING

Read full text Summarise with VIRAT
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

Loneliness is a significant health issue on the general population that is associated with depression, anxiety, immune malfunction, and deaths.Consecutive and scalable monitoring is constrained by traditional evaluation tools, like selfreport scales.The most recent developments of transformer-based Natural Language Processing models such as BERT and RoBERTa, allow better contextual interpretation of digital text, which can be used to detect the state of a person with automated methods.Nevertheless, the interpretable fine-grained loneliness detection is not abundant.The proposed study is an Explainable AI framework that uses a transformer to combine contextual sentiment analysis and behavioral metadata to identify early loneliness with the additions of SHAP-based interpretability.The experimental outcomes prove to be better than the traditional machine learning baselines, whereas the use of AI-based mitigation measures, including digital support systems, improves the potential of intervention in the real world.

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