Predicting Stress at Workplace using Machine Learning Techniques
Authors:
- 6 July 2023
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
Abstract
Work stress is a common issue nowadays among working professionals, especially with the changing environment, and culture. This type of stress occurs in a wide range of circumstances, but the majority are not aware of the ‘Stress Management’ techniques to deal with it. With this paper, the aim is to create awareness about such techniques and further work on the available treatment by using different machine learning algorithms like Support Vector Machine, Decision Tree, Gradient Boost, etc. A survey is done of working professionals regarding the level of stress, various stress management policies present in the workplace and the awareness about the role of artificial intelligence or machine learning for handling stress. This has indicated an important need of stress management at the workplace and the role of AI for its identification. Various machine learning algorithms are used to identify mental health issues. The result presented is based on the execution of these algorithms on data from the OSMI Mental Health Survey 2021 conducted among working professionals in the tech industry and the result is drawn as a comparison to the existing work on the same data from OSMI Mental Health Survey 2014 after training different ML models for accuracy. Best results are identified with decision tree algorithm.Keywords
This publication has 13 references indexed in Scilit:
- Improvement of Support Vector Machine Algorithm in Big Data BackgroundMathematical Problems in Engineering, 2021
- Predicting the Utilization of Mental Health Treatment with Various Machine Learning AlgorithmsWSEAS TRANSACTIONS ON COMPUTERS, 2021
- AdaBoost typical Algorithm and its application researchMATEC Web of Conferences, 2017
- Workplace interventions for common mental disorders: a systematic meta-reviewPsychological Medicine, 2015
- Social media as a measurement tool of depression in populations2013
- Gradient boosting machines, a tutorialFrontiers in Neurorobotics, 2013
- A Synthesis of the Evidence for Managing Stress at Work: A Review of the Reviews Reporting on Anxiety, Depression, and AbsenteeismJournal of Environmental and Public Health, 2012
- Logistic regression in data analysis: an overviewInternational Journal of Data Analysis Techniques and Strategies, 2011
- Data Cleaning: Detecting, Diagnosing, and Editing Data AbnormalitiesPLOS Medicine, 2005
- Analysis and compensation of speech under stress and noise for environmental robustness in speech recognitionSpeech Communication, 1996