Mental Illness Prediction using Myers Briggs Personality Indicators

Personality has a significant weightage in our lives. It determines our cognitive abilities which directly affect our behaviour and our preferences and even affects our mental health. This project aims to predict users’ mental health and MBTI personality using text inserted by the users via a web application. Utilizing Label Encoder and Count vectorizer, data was encoded. The machine learning model with the greatest accuracy score has been chosen. Several machine learning models were created and trained on the data-set, including Logistic Regression, SVM, Random Forest, Naive Bayes, and K-Neighbors Classifier. The XG-Boost classifier predicts 16 different personality types across four axes based on introversion, intuition, reasoning, and perceived abilities, even when tested on the same dataset. The accuracy which was predicted given by k fold Cross Validation shows that the XG-Boost classifier gives the best accuracy of 67.68 percent for prediction of the personality