• Pranav Srivastava
• Pragati Mani Tripathi
• Rajat Singh
• Jaya Agrawal
• Pallavi Dixit

In today's fast-paced modern world, mental health issues such as anxiety, depression, and stress have become very common in the general population. In this article, predictions of anxiety, depression, and stress were made using machine learning algorithms. By applying these algorithms to, data was collected from employed and unemployed people across cultures and communities via the Depression, Anxiety and Stress Scale Questionnaire (DASS 21). Anxiety, depression, and stress were predicted by five different machine learning algorithms at five levels of severity - and because of their high accuracy they are particularly good at predicting psychological problems. After applying different methods, classes were found to be unbalanced in the confusion matrix. Therefore, the f1-score metric has been added, which helps to determine the best accuracy model among the five algorithms applied as a random forest classifier. Additionally, the specificity parameter indicates that the algorithm is also particularly sensitive to negative results.

Machine Learning, Mental Health, Supervised Learning, Vector Machine

"A survey on mental health prediction", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.10, Issue 5, page no.g114-g119, May-2023, Available :http://www.jetir.org/papers/JETIR2305616.pdf

"A survey on mental health prediction", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.10, Issue 5, page no. ppg114-g119, May-2023, Available at : http://www.jetir.org/papers/JETIR2305616.pdf