Unsupervised Learning Approaches for Analyzing Mental Health Patterns in Professional Environments: A Comparative Study of Clustering Architectures

Read full text Summarise with VIRAT
Authors: Rahman, Mohammad, Ziaur, Abdullah Rakib Akand, Hossain Simanto, Sherin Sheela, Sudeepon Roy, Shariya Chowdhury, Ahmed Faizul, Haque Dhrubo, Abdullah Al Imtihan, Mithila Arman
Cited by: 0
References: 27

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

The intersection of workplace dynamics and mental health has become a critical area of research, particularly as rates of depression among professionals continue to rise. This paper presents a comprehensive comparative analysis of unsupervised machine learning algorithms designed to identify latent patterns and risk profiles within a high-dimensional professional depression dataset. We rigorously evaluate three distinct clustering architectures: K-Means (partition-based), Agglomerative Nesting (AGNES, hierarchical), and Density-Based Spatial Clustering of Applications with Noise (DBSCAN). The methodology incorporates advanced preprocessing techniques, including SelectKBest feature selection and robust standardization. We utilize Silhouette Scores, cluster stability metrics, and visual validation to assess algorithmic performance. Our findings reveal that while partitionbased methods (K-Means) offer superior separation for spherical clusters in this domain (Silhouette Score: 0.452), DBSCAN provides crucial insights into outlier detection, identifying unique, high-risk cases that traditional methods overlook. By employing unsupervised learning, we aim to uncover hidden structures in the data that correspond to different risk profiles-for instance, distinguishing between "high-functioning" stress and clinical depression. This study contributes a novel, data-driven framework for mental health surveillance in corporate environments.

Fields of Study & Subjects

Advanced Clustering Algorithms Research Artificial Intelligence in Healthcare Data Mining and Machine Learning Applications

Publication details

Journal / source
HAL
Publication date
26 February 2026
Language
EN