From Questionnaires to Actionable Insights: Machine Learning for Mental Stress Detection
Received: 19 July 2025 | Revised: 30 July 2025, 28 August 2025, and 8 September 2025 | Accepted: 9 September 2025 | Online: 14 October 2025
Corresponding author: Sumit Sudhakar Shinde
Abstract
Mental stress is a pervasive global health concern, necessitating timely and accurate detection for effective intervention and well-being. While questionnaire-based assessments are widely employed by medical practitioners, their efficacy can be influenced by questionnaire quality and assessor expertise. Addressing a notable research gap in the application of Machine Learning (ML) for mental stress assessment within the specific context of the Indian population, this study proposes a novel ML-based approach. Our methodology leverages comprehensive input data derived from Depression Anxiety and Stress-42 (DASS-42) questionnaire responses, Ten Item Personality Inventory (TIPI) questions, and relevant demographic factors. An ensemble voting classifier, integrating Logistic Regression (LR), Support Vector Machines (SVMs), Random Forest (RF), and Extreme Gradient Boosting (XGBoost), was developed as the predictive model. Model robustness was rigorously evaluated using k-fold cross-validation, revealing consistent performance with a mean accuracy of 94.5% and a low standard deviation of 2.5%. Hyperparameters were meticulously tuned using grid search to optimize the ensemble's performance, resulting in a classification accuracy of 95% for mental stress detection. Furthermore, the model's predictions demonstrated a strong positive correlation (Pearson correlation coefficient of 0.822729) with results obtained from the standard Patient Health Questionnaire-9 (PHQ-9) questionnaire, statistically confirming its validity and alignment with established clinical assessments. This research offers a robust and validated decision support system that can aid mental health professionals in early diagnosis, guide customized preventive actions, and contribute significantly to destigmatizing mental health issues, thereby promoting overall mental well-being in diverse populations.
Keywords:
mental stress, Machine Learning (ML), questionnaires, Depression Anxiety and Stress Scale-42 (DASS-42), Patient Health Questionnaire-9 (PHQ-9), ensemble classifiersDownloads
References
K. Kroenke, R. L. Spitzer, and J. B. W. Williams, "The PHQ-9," Journal of General Internal Medicine, vol. 16, no. 9, pp. 606–613, Sep. 2001. DOI: https://doi.org/10.1046/j.1525-1497.2001.016009606.x
S. H. Lovibond and P. F. Lovibond, Manual for the Depression Anxiety Stress Scales, 2nd ed. Sydney, Australia: Psychology Foundation of Australia, 1995. DOI: https://doi.org/10.1037/t01004-000
R. L. Spitzer, K. Kroenke, J. B. W. Williams, and B. Löwe, "A Brief Measure for Assessing Generalized Anxiety Disorder: The GAD-7," Archives of Internal Medicine, vol. 166, no. 10, pp. 1092–1097, May 2006. DOI: https://doi.org/10.1001/archinte.166.10.1092
P. Anderson et al., "Improving the delivery of brief interventions for heavy drinking in primary health care: outcome results of the Optimizing Delivery of Health Care Intervention (ODHIN) five-country cluster randomized factorial trial," Addiction, vol. 111, no. 11, pp. 1935–1945, Nov. 2016. DOI: https://doi.org/10.1111/add.13476
A. J. Mitchell and J. C. Coyne, "Do ultra-short screening instruments accurately detect depression in primary care?: A pooled analysis and meta-analysis of 22 studies," British Journal of General Practice, vol. 57, no. 535, pp. 144–151, Feb. 2007.
A. Singh and D. Kumar, "Identification of Anxiety and Depression Using DASS-21 Questionnaire and Machine Learning," in 2021 First International Conference on Advances in Computing and Future Communication Technologies, Meerut, India, 2021, pp. 69–74. DOI: https://doi.org/10.1109/ICACFCT53978.2021.9837365
K. S. Srinath, K. Kiran, S. Pranavi, M. Amrutha, P. D. Shenoy, and K. R. Venugopal, "Prediction of Depression, Anxiety and Stress Levels Using Dass-42," in 2022 IEEE 7th International conference for Convergence in Technology, Mumbai, India, 2022, pp. 1–6. DOI: https://doi.org/10.1109/I2CT54291.2022.9824087
K. Singh, M. Junnarkar, and S. Sharma, "Anxiety, stress, depression, and psychosocial functioning of Indian adolescents," Indian Journal of Psychiatry, vol. 57, no. 4, Dec. 2015, Art. no. 367. DOI: https://doi.org/10.4103/0019-5545.171841
S. Amudhan and G. Gopalkrishna, "Depression in India: Let’s talk." World Health Organization, 2017.
S. Rao and N. Ramesh, "Depression, anxiety and stress levels in industrial workers: A pilot study in Bangalore, India," Industrial Psychiatry Journal, vol. 24, no. 1, Jun. 2015, Art. no. 23. DOI: https://doi.org/10.4103/0972-6748.160927
M. Sahu, B. Chattopadhyay, R. Das, and S. Chaturvedi, "Measuring Impact of Climate Change on Indigenous Health in the Background of Multiple Disadvantages: A Scoping Review for Equitable Public Health Policy Formulation," Journal of Prevention, vol. 44, no. 4, pp. 421–456, Aug. 2023. DOI: https://doi.org/10.1007/s10935-022-00718-8
J. N. Al-Karaki, A. Gawanmeh, M. Ayache, and A. Mashaleh, "DASS-CARE: A Decentralized, Accessible, Scalable, and Secure Healthcare Framework using Blockchain," in 2019 15th International Wireless Communications & Mobile Computing Conference, Tangier, Morocco, 2019, pp. 330–335. DOI: https://doi.org/10.1109/IWCMC.2019.8766714
M. Ayache, A. Gawanmeh, and J. N. Al-Karaki, "DASS-CARE 2.0: Blockchain-Based Healthcare Framework for Collaborative Diagnosis in CIoMT Ecosystem," in 2022 5th Conference on Cloud and Internet of Things, Marrakech, Morocco, 2022, pp. 40–47. DOI: https://doi.org/10.1109/CIoT53061.2022.9766532
S. Jain, S. P. Narayan, R. K. Dewang, U. Bhartiya, N. Meena, and V. Kumar, "A Machine Learning based Depression Analysis and Suicidal Ideation Detection System using Questionnaires and Twitter," in 2019 IEEE Students Conference on Engineering and Systems, Allahabad, India, 2019, pp. 1–6. DOI: https://doi.org/10.1109/SCES46477.2019.8977211
R. S. Skaik and D. Inkpen, "Predicting Depression in Canada by Automatic Filling of Beck’s Depression Inventory Questionnaire," IEEE Access, vol. 10, pp. 102033–102047, 2022. DOI: https://doi.org/10.1109/ACCESS.2022.3208470
B. Sahoo and A. Gupta, "An Ensemble Kernelized-based Approach for Precise Emotion Recognition in Depressed People," Engineering, Technology & Applied Science Research, vol. 14, no. 6, pp. 18873–18882, Dec. 2024. DOI: https://doi.org/10.48084/etasr.8785
R. Bidwe, S. Mishra, S. Bajaj, and K. Kotecha, "Leveraging hybrid model of ConvNextBase and LightGBM for early ASD detection via eye-gaze analysis," MethodsX, vol. 14, Jun. 2025, Art. no. 103166. DOI: https://doi.org/10.1016/j.mex.2025.103166
R. Vasant Bidwe, S. Mishra, S. Kamini Bajaj, and K. Kotecha, "Attention-Focused Eye Gaze Analysis to Predict Autistic Traits Using Transfer Learning," International Journal of Computational Intelligence Systems, vol. 17, no. 1, May 2024, Art. no. 120. DOI: https://doi.org/10.1007/s44196-024-00491-y
"Open psychology data: Raw data from online personality tests." Openpsychometrics. https://openpsychometrics.org/_rawdata/.
A. Sau and I. Bhakta, "Screening of anxiety and depression among seafarers using machine learning technology," Informatics in Medicine Unlocked, vol. 16, Jan. 2019, Art. no. 100228. DOI: https://doi.org/10.1016/j.imu.2019.100228
Md. S. Zulfiker, N. Kabir, A. A. Biswas, T. Nazneen, and M. S. Uddin, "An in-depth analysis of machine learning approaches to predict depression," Current Research in Behavioral Sciences, vol. 2, Nov. 2021, Art. no. 100044. DOI: https://doi.org/10.1016/j.crbeha.2021.100044
A. Priya, S. Garg, and N. P. Tigga, "Predicting Anxiety, Depression and Stress in Modern Life using Machine Learning Algorithms," Procedia Computer Science, vol. 167, pp. 1258–1267, Jan. 2020. DOI: https://doi.org/10.1016/j.procs.2020.03.442
Downloads
How to Cite
License
Copyright (c) 2025 Sumit Sudhakar Shinde, Archana Santosh Ghotkar
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain the copyright and grant the journal the right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) after its publication in ETASR with an acknowledgement of its initial publication in this journal.
