Anxiety and Depression Detection using Machine Learning

ABSTRACT

Anxiety and Depression are among the extremely crucial mental health issues. Every year, millions of individuals suffer from depression and anxiety, yet only a small percentage of them receive timely treatment. Throughout the last few decades, the evolution of machine learning methods has considerably aided in the development of technologies that assist clinicians in predicting various sorts of mental illnesses. As the Covid-19 pandemic rapidly spreads over the world, the global gaming industry is booming. Youth is increasingly focused on digital games due to lockdown and social distancing policies. This work presents a system for predicting if a player suffers from psychological illnesses such as anxiety and depression by combining game and player information with a selfesteem measure. The game and player's data has been gathered from two questionnaires namely, GAD and SWL, and multiple state-of-the-art simulations have been conducted. Four different machine learning classifiers were tested using 10-fold cross-validation approach on data set of internet gamers. Among the four algorithms, Decision Tree classifier showed the best accuracy for all predicted parameters. For GAD and SWL questionnaires, decision tree obtains accuracy of 100% and 84.71% respectively. © 2022 IEEE.