A Machine Learning Approach to Assess Psychological State Among University Students Throughout the Covid-19 Pandemic - Bangladesh

Aug 5, 2026

Upload by Miles

The COVID-19 outbreak in Bangladesh produced clear harms to mental health across age groups, with university students experiencing sustained psychological strain. During pandemic lockdowns, students faced disrupted education, limited sports and entertainment access, and reduced wellbeing supports, contributing to elevated stress, anxiety, and depression. This study builds an online-survey dataset and applies machine learning models to predict psychological states, using cleaned data and hyperparameter tuning. Trained classifiers, especially SVC, achieve strong AUROC values for depression, anxiety, and stress while maintaining participant ethics and privacy.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages7

Reading Time18 min

AccessFree to download

Introduction

Psychological impact during COVID-19 in Bangladesh

Prior work and related studies

Study objective

A Machine Learning Approach to Assess Psychological State Among University Students Throughout the Covid-19 Pandemic: Bangladesh Perspective ‘ Anower Hossen Computer Science & Engineering International Islamic University Chittagong Chattogram, Bangladesh [a.h.sumon2607@gmail.com](a.h.sumon2607@gmail.com) Rahim Uddin Rafin Computer Science & Engineering International Islamic University Chittagong Chattogram, Bangladesh [rafinc10@gmail.com](rafinc10@gmail.com) Shahidul Islam Khan Computer Science & Enginneering International Islamic University Chittagong Chattogram, Bangladesh [nayeemkh@gmail.com](nayeemkh@gmail.com) Mahin Mahtab Computer Science & Engineering International Islamic University Chittagong Chattogram, Bangladesh [mahin.mahtab.1@gmail.com](mahin.mahtab.1@gmail.com) Abstract - The COVID-19 outbreak in Bangladesh had a negative impact on people of all ages. The epidemic's destruction clearly had an effect on people's mental health, especially that of university students. From the beginning of the pandemic in Bangladesh, educational institutes were shut down, complete lockdown condition, unable to get sports and entertainment abilities, which caused the student's psychological health to suffer. Most university-aged students exhibited long-lasting psychological issues corresponding with COVID-19, including significant levels of stress, anxiety, and depression. Predicting the psychological state will indicate a lack of psychological resilience, which will be associated with mental health problems among Bangladeshi university students. Increasing psychological fortitude is essential to ensuring pupils' well-being throughout the epidemic. Through an online survey and several machine learning algorithms, our system predicts the psychological state of Bangladeshi university students. Wepreprocessed this dataset by cleaning it correctly for the procedure. We utilized hyper-parameter tweaking to extract the features, and then we trained the dataset using a number ofclassifiers, such as the support vector classifier, random forest, logistic regression, decision tree, naive Bayes, KNN, and gradient boosting. Study suggests that, these algorithms works best in researching on mental health related datasets. Among these several machine learning algorithms, our created dataset of 509 points, comprising support vector classifier (SVC), produced an AUROC score of 0.98, 0.97, and 0.97 for depression, anxiety, and stress states, respectively. Additionally, SVC also delivered respectable outcomes on the open-source dataset we collected for each of the psychological states - depression, anxiety, and stress. Support vector machine (SVM), a supervised machine learning model that employs classification methods, may, in general, produce excellent results when there is a distinct proportion of displacement between classes. By evaluating adataset we have collected and enhancing the DASS-21 formulation to measure an individual's depression, anxiety, and stress. DAAS-21 is well established screening method for addressing mental health issue. We sincerely considered the ethics and all the data we collected from people are preserved with care and utmost privacy. This study will aid in the growth of research into the area of suicidal thoughts and emotional states. Keywords: SVC, KNN, GB, DT, Random Forest, Logistic Regression, DASS-21, Depression, Stress, Anxiety, Hyperparameter Tuning I. INTRODUCTION University students have experienced greater levels of worry, psychological stress, and sadness as a result of the pandemic's effects on people's mental health [3] . A sufficient number of studies that take into account the main components of a psychological state, such as stress, anxiety, and depression, have not yet been discovered, according to the Bangladeshi viewpoint, since the majority of Bangladeshi publications and papers focus on physical rather than psychological difficulties, such as pulse rate, systolic and diastolic

FAQs

Why focus on university students’ psychological state during Bangladesh’s COVID-19 pandemic?

Educational shutdowns and lockdown restrictions disrupted daily routines and support systems, contributing to long-lasting stress, anxiety, and depression among university-aged students.

How is psychological state measured in the study?

The study uses the DASS-21 questionnaire to assess depression, anxiety, and stress, then maps those labels to machine learning predictions.

Which machine learning approach performs best and how is it evaluated?

A support vector classifier (SVC) achieves high AUROC scores for depression, anxiety, and stress, and the system also reports strong results on collected open-source datasets.

Aug 5, 2026

Upload by Miles