Prediction of Mental Health Issues and Challenges Using Hybrid Machine and Deep Learning Techniques

Mental health issues like melancholy, anxiety, and a lack of sleep in young children, teenagers, and adults are the root causes of emotional stress. It influences a person's feelings, thoughts, or reactions to a particular event or scenario. Being in good physical and mental health is a prerequisite for productive work and realizing one's full potential. From childhood to maturity, maintaining one's mental health is crucial. The various causes of mental health concerns that lead to mental illness include stress, social anxiety, depression, obsessive–compulsive disorder, substance addiction, employment issues, and personality disorders. We used openly accessible web datasets to collect the data. The data was label-encoded to improve prediction. The methods employed include logistic regression, Nave Bayes, decision trees, neural networks, and support vector machines. The Decision Tree, the Support Vector Machine, and the neural network, in that order, are the most trustworthy models for stress, depression, and anxiety. The data is put through several machine-learning techniques to produce labels. Based on these classified categories, a model will be created to forecast the mental state of an individual. People over 18 who are working class make up our primary market after finishing, based on the information a user submitted on the website.