Paper Title
DETECTION OF MENTAL HEALTH ISSUES ON SOCIAL MEDIAUSING MACHINE LEARNING METHODS
Abstract
Given the increasing occurrence of mental health disorders and their profound impact on individuals and society, it is imperative to develop efficient methods for promptly addressing them. The objective of this work is to identify and emphasize on mental health concerns by analyzing the extensive amount of user-generated information. In addition, we implemented the suggested approach by creating a prototype called the Mental Health Detector. The Kaggle platform provided a collection of Twitter datasets, consisting of 28,536 tweets that were free from any unwanted content. Multiple machine learning methods were employed to train and evaluate the dataset. The results demonstrate that Logistic Regression is the most effective predictive model, achieving an accuracy of 89.03%, a precision of 89.19%, a recall of 89.03%, and an F1- score of 88.97%.
Keywords – Mental Health, Twitter, Stress, Anxiety, Depression, Machine Learning.