Predicting Stress in Bangladeshi University Students: A LIME-Interpretable Machine Learning Approach

This dataset was collected as part of the study:
Predicting Stress in Bangladeshi University Students: A LIME-Interpretable Machine Learning Approach (https://www.researchgate.net/publication/383053109_Predicting_Stress_in_Bangladeshi_University_Students_A_LIME-Interpretable_Machine_Learning_Approach)

Description
The dataset contains responses from 571 students from various public, private, and national universities in Bangladesh, collected between September 2022 and January 2023 via an online survey (Google Form).

It is designed to predict and analyze stress levels among university students using:

DASS-21 (Bangla Version) – for stress level assessment

Ten-Item Personality Inventory (TIPI) – for personality traits

Additional demographic and lifestyle factors

Structure

Demographics – Academic year, age, CGPA, university type, etc.

Stress Factors – Living arrangements, academic satisfaction, financial difficulties, exposure to violence, bullying, relationship issues, social media use, etc.

DASS-21 Items – 7 questions (Q1A–Q7A)

TIPI Items – 10 questions (TIPI1–TIPI10)

Target Variable – Stress level:

Normal (0–18)

Moderate (19–25)

Severe (26+)

Potential Uses

Stress level classification

Personality–stress correlation analysis

Feature importance analysis with XAI (LIME, SHAP)

Academic performance impact analysis

Citation
If you use this dataset, please cite:
Hosen, M.H., Islam, M.T., Ashraf, K., & Haque, P. (2024). Predicting Stress in Bangladeshi University Students: A LIME-Interpretable Machine Learning Approach. ResearchGate. https://doi.org/10.13140/RG.2.2.32712.62727

Ask ChatGPT