Researchers develop new 'emotionally aware' model for classifying mental health conditions

by Andy Cain, Keele University

edited by Lisa Lock, reviewed by Andrew Zinin

Lisa Lock

Scientific Editor

Meet our editorial team
Behind our editorial process

Andrew Zinin

Lead Editor

Meet our editorial team
Behind our editorial process Editors' notes

This article has been reviewed according to Science X's editorial process and policies. Editors have highlighted the following attributes while ensuring the content's credibility:

fact-checked

trusted source

proofread

The GIST Add as preferred source

Researchers have developed a new "emotionally aware" AI-based model for classifying mental health conditions, which could help clinicians better diagnose patients' mental health conditions. The Emo-MHC model uses machine learning (ML) and deep learning (DL) techniques to analyze text from sources like doctors' notes, social media posts and online forums to help doctors classify patients' mental health conditions more accurately and quickly than existing models, which could help provide more effective care.

Many models already use a combination of natural language processing and machine learning to classify mental health conditions, but as many of these rely on self-assessments and standardized clinical tests, they can be inaccurate at classifying mental health conditions.

In some cases, an analysis like this may also miss certain emotional nuances or misinterpret emotions, leading to an incomplete or inaccurate classification, which will in turn affect a patient's treatment plan and potentially their recovery.

The Emo-MHC model was jointly developed by Dr. Shaily Kabir of the University of Nottingham and Dr. Sangeeta Sangeeta of Keele University, in collaboration with students Joy Paul and Zerin Jahan.

The model is different in that it uses advanced emotion detection and lexicon-based text analysis to reduce the risk of these emotional details being misread or omitted, resulting in more accurate classification of mental health conditions.

The researchers tested the model on publicly available datasets and found it could classify mental health conditions with 92% accuracy, outperforming the benchmark by about 8 percentage points. Their findings are published in the 2026 International Conference on Innovations in Computational Intelligence (ICICI).

The researchers now want to refine the model further to make it even more accurate and assess how it could be used to help more patients dealing with mental health conditions.

Sangeeta, author and lecturer in data science at Keele University, said, "Rates of mental health conditions are increasing, highlighting the urgent need for robust methods that enable accurate early detection. In the era of artificial intelligence and large language models, these technologies have significant potential to support individuals experiencing mental health challenges. Improved diagnostic accuracy can not only reduce the burden on the NHS but also play a critical role in saving lives."

More information

Joy Paul et al, Emo-MHC: Emotion-Driven Text-Based Classification of Mental Health Conditions using Machine Learning and Deep Learning Techniques, 2026 International Conference on Innovations in Computational Intelligence (ICICI) (2026). DOI: 10.1109/icici68867.2026.11564958

Key medical concepts

Mental Disorders

Clinical categories

PsychiatryPsychology & Mental health Provided by Keele University Who's behind this story?

Lisa Lock

BA art history, MA material culture. Former museum editor, paramedic, and transplant coordinator. Editing for Science X since 2021. Full profile →

Andrew Zinin

Master's in physics with research experience. Long-time science news enthusiast. Plays key role in Science X's editorial success. Full profile →

Citation: Researchers develop new 'emotionally aware' model for classifying mental health conditions (2026, June 22) retrieved 29 June 2026 from https://medicalxpress.com/news/2026-06-emotionally-aware-mental-health-conditions.html This document is subject to copyright. Apart from any fair dealing for the purpose of private study or research, no part may be reproduced without the written permission. The content is provided for information purposes only.