Identification of Mental Disorder based on Changes in Personal Behaviour using Machine Learning

People are having behavioral issues and mental disorders as a result of increased strain and stress in their daily lives. Anxiety, Depression, Stress, Schizophrenia, Bipolar Disorder, and many more types of Mental Disorders exist. There are various types of physical and emotional symptoms in mental disorder. This research will identify mental illness based on the occurrences and feelings that a person is experiencing. Panic attacks, sweating, palpitations, sorrow, anxiety, overthinking, hallucinations, and illusions are all signs of mental disease, and each symptom reveals something about the kind of mental illness. The (Feed Forward Neural Network)FFNN, XGBoost, Support Vector Machine, Logistic Regression, and Decision Tree are five machine learning algorithms used in this study. We used an additional tree classifier as a feature selection approach in this study, along with other preprocessing procedures. Following the feature selection approach, a machine learning algorithm was used to diagnose a mental illness based on the person’s symptoms. The effectiveness of machine learning models was assessed using the Recall, Accuracy, Precision, and F1-score parameters. Logistic regression produced the greatest results, with an accuracy of 79.9%, while the FFNN model had the lowest accuracy of 40.9%