2023
doi: 10.12720/jait.14.3.571-580
DASS-21 Based Psychometric Prediction Using Advanced Machine Learning Techniques
Jayshree Ghorpade-Aher*
,
Ahbaz Memon ,
Snehalraj Chugh ,
Abhishek Chebolu ,
Prajakta Chaudhari ,
Janhavi Chavan
- Dr. Vishwanath Karad MIT World Peace University, Pune, India
- Manuscript receivedAugust 10, 2022
- revisedSeptember 22, 2022
- acceptedOctober 14, 2022
- publishedJune 25, 2023
Abstract
The Depression, Anxiety, and Stress Scales (DASS) are 3-factor paradigms; the research is about understanding an individual’s instant, psychic response to the epidemic in evaluating their mental health. Anxiety, stress, and depression in adults over the age of eighteen are the primary subjects of this study. In computing behaviourism, it’s critical to analyse individuals’ emotional responses to strain and forecast how they will respond. 39,775 responses from individuals were obtained for the research data who took part in experiments between 2017 and 2019. When connecting attributes to anxiety levels, nearly seven distinct advanced Machine Learning (ML) based classifying algorithms were applied for experimentation. Further Artificial Intelligence (AI) techniques were used to substantially increase the accuracy of the research work. Ada-boost categorising with Support Vector Machine (SVM) base and SVM classification algorithms had a maximum predictive performance of 96% in Machine Learning models. The model acquired the highest results and the quickest time to prepare the entire collection after using Deep Learning (DL) algorithms.
Keywords
- DASS-21
- Adaboost
- support vector machine classifier
- psychology
- convolution neural network
- naïve bayes
How to Cite
Jayshree Ghorpade-Aher, Ahbaz Memon, Snehalraj Chugh, Abhishek Chebolu, Prajakta Chaudhari, and Janhavi Chavan, "DASS-21 Based Psychometric Prediction Using Advanced Machine Learning Techniques," Journal of Advances in Information Technology, vol. 14, no. 3, pp. 571-580, 2023. https://doi.org/10.12720/jait.14.3.571-580
Copyright & License
Copyright © 2023 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).
