Categorizing Mental Stress: A Consistency-Focused Benchmarking of ML and DL Models for Multi-Label, Multi-Class Classification via Taxonomy-Driven NLP Techniques

Mental stress, a critical concern worldwide, necessitates precise and nuanced characterization. This study introduces a novel approach to effectively characterize mental stress through a multi-label, multi-class classification framework through natural language processing techniques. Building on exi...

Full description

Saved in:
Bibliographic Details
Main Authors: Juswin Sajan John, Boppuru Rudra Prathap, Gyanesh Gupta, Jaivanth Melanaturu
Format: Article
Language:English
Published: Elsevier 2025-06-01
Series:Natural Language Processing Journal
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S294971912500038X
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850118653938237440
author Juswin Sajan John
Boppuru Rudra Prathap
Gyanesh Gupta
Jaivanth Melanaturu
author_facet Juswin Sajan John
Boppuru Rudra Prathap
Gyanesh Gupta
Jaivanth Melanaturu
author_sort Juswin Sajan John
collection DOAJ
description Mental stress, a critical concern worldwide, necessitates precise and nuanced characterization. This study introduces a novel approach to effectively characterize mental stress through a multi-label, multi-class classification framework through natural language processing techniques. Building on existing literature, discussions with psychologists and other mental health practitioners, we developed a taxonomy of 27 distinctive markers spread across 4 label categories; aiming to create a preliminary screening tool leveraging textual data.The core objective is to identify the most suitable model for this complex task, encompassing comprehensive evaluation of various machine learning and deep learning algorithms. we experimented with support vector machines (SVM), random forest (RF) and long short-term memory (LSTM) algorithms incorporating various feature combinations involving Term Frequency-Inverse Document Frequency (TF-IDF) and Latent Dirichlet Allocation (LDA). The best performer of this comparative study was further evaluated against an LLM.The potential of large language models (LLMs), including their language understanding and prediction capabilities, is another key focus. We explore how these models could augment and advance mental health research, offering new perspectives and insights into the characterization of mental stress.Our findings show that the top model, an LSTM with TF-IDF and LDA (class weights assigned) outperformed the PaLM model with a coefficient of variation as low as 0.87% across all labels. Despite the PaLM model’s superior average performance, it exhibited higher variability among different labels.
format Article
id doaj-art-3df2335fad2a45f3b7e1d1ceb760121c
institution OA Journals
issn 2949-7191
language English
publishDate 2025-06-01
publisher Elsevier
record_format Article
series Natural Language Processing Journal
spelling doaj-art-3df2335fad2a45f3b7e1d1ceb760121c2025-08-20T02:35:48ZengElsevierNatural Language Processing Journal2949-71912025-06-011110016210.1016/j.nlp.2025.100162Categorizing Mental Stress: A Consistency-Focused Benchmarking of ML and DL Models for Multi-Label, Multi-Class Classification via Taxonomy-Driven NLP TechniquesJuswin Sajan John0Boppuru Rudra Prathap1Gyanesh Gupta2Jaivanth Melanaturu3Department of Computer Science and Engineering, CHRIST UNIVERSITY, Bengaluru, IndiaDepartment of Computer Science and Engineering, M. S. Ramaiah University of Applied Sciences, Bengaluru, India; Corresponding author.Department of Computer Science and Engineering, CHRIST UNIVERSITY, Bengaluru, IndiaDepartment of Computer Science and Engineering, CHRIST UNIVERSITY, Bengaluru, IndiaMental stress, a critical concern worldwide, necessitates precise and nuanced characterization. This study introduces a novel approach to effectively characterize mental stress through a multi-label, multi-class classification framework through natural language processing techniques. Building on existing literature, discussions with psychologists and other mental health practitioners, we developed a taxonomy of 27 distinctive markers spread across 4 label categories; aiming to create a preliminary screening tool leveraging textual data.The core objective is to identify the most suitable model for this complex task, encompassing comprehensive evaluation of various machine learning and deep learning algorithms. we experimented with support vector machines (SVM), random forest (RF) and long short-term memory (LSTM) algorithms incorporating various feature combinations involving Term Frequency-Inverse Document Frequency (TF-IDF) and Latent Dirichlet Allocation (LDA). The best performer of this comparative study was further evaluated against an LLM.The potential of large language models (LLMs), including their language understanding and prediction capabilities, is another key focus. We explore how these models could augment and advance mental health research, offering new perspectives and insights into the characterization of mental stress.Our findings show that the top model, an LSTM with TF-IDF and LDA (class weights assigned) outperformed the PaLM model with a coefficient of variation as low as 0.87% across all labels. Despite the PaLM model’s superior average performance, it exhibited higher variability among different labels.http://www.sciencedirect.com/science/article/pii/S294971912500038XMental stressNatural language processingMachine learningDeep learningMental health researchLLM
spellingShingle Juswin Sajan John
Boppuru Rudra Prathap
Gyanesh Gupta
Jaivanth Melanaturu
Categorizing Mental Stress: A Consistency-Focused Benchmarking of ML and DL Models for Multi-Label, Multi-Class Classification via Taxonomy-Driven NLP Techniques
Natural Language Processing Journal
Mental stress
Natural language processing
Machine learning
Deep learning
Mental health research
LLM
title Categorizing Mental Stress: A Consistency-Focused Benchmarking of ML and DL Models for Multi-Label, Multi-Class Classification via Taxonomy-Driven NLP Techniques
title_full Categorizing Mental Stress: A Consistency-Focused Benchmarking of ML and DL Models for Multi-Label, Multi-Class Classification via Taxonomy-Driven NLP Techniques
title_fullStr Categorizing Mental Stress: A Consistency-Focused Benchmarking of ML and DL Models for Multi-Label, Multi-Class Classification via Taxonomy-Driven NLP Techniques
title_full_unstemmed Categorizing Mental Stress: A Consistency-Focused Benchmarking of ML and DL Models for Multi-Label, Multi-Class Classification via Taxonomy-Driven NLP Techniques
title_short Categorizing Mental Stress: A Consistency-Focused Benchmarking of ML and DL Models for Multi-Label, Multi-Class Classification via Taxonomy-Driven NLP Techniques
title_sort categorizing mental stress a consistency focused benchmarking of ml and dl models for multi label multi class classification via taxonomy driven nlp techniques
topic Mental stress
Natural language processing
Machine learning
Deep learning
Mental health research
LLM
url http://www.sciencedirect.com/science/article/pii/S294971912500038X
work_keys_str_mv AT juswinsajanjohn categorizingmentalstressaconsistencyfocusedbenchmarkingofmlanddlmodelsformultilabelmulticlassclassificationviataxonomydrivennlptechniques
AT boppururudraprathap categorizingmentalstressaconsistencyfocusedbenchmarkingofmlanddlmodelsformultilabelmulticlassclassificationviataxonomydrivennlptechniques
AT gyaneshgupta categorizingmentalstressaconsistencyfocusedbenchmarkingofmlanddlmodelsformultilabelmulticlassclassificationviataxonomydrivennlptechniques
AT jaivanthmelanaturu categorizingmentalstressaconsistencyfocusedbenchmarkingofmlanddlmodelsformultilabelmulticlassclassificationviataxonomydrivennlptechniques