Predictive Analysis on Student's Mental Health Towards Online Mobile Games Using Machine Learning

With the advancement of technology, online mobile games have gained immense popularity in recent years, attracting players of various age groups, from young individuals to adults. These games now boast captivating graphics and immersive features designed to entice a large user base. However, a growing concern arises as many students become addicted to these online games, leading to detrimental effects on their mental health. The addiction to mobile games not only impacts their psychological well-being but also gives rise to physical health issues due to prolonged sedentary behavior. Our research paper addresses this pressing problem by proposing an algorithm that analyzes the level of addiction based on three crucial factors: depression, social anxiety, and loneliness. By examining these factors, we can gain valuable insights into the addictive tendencies exhibited by individuals. To evaluate the addiction level, we employed three widely-used machine learning algorithms: Logistic Regression (LR), Ridge Regression (RR), and Support Vector Machine (SVM). Through our rigorous analysis, it was evident that the SVM algorithm surpassed the others, achieving an impressive accuracy rate of 91.68%. In order to promote better mental health among students, it is crucial to address these underlying factors and encourage them to engage in mobile gaming for a limited duration.