A HYBRID APPROACH FOR PREDICTING MENTAL HEALTH DISORDERS USING SOCIAL MEDIA DATA AND ENSEMBLE LEARNING TECHNIQUES

Data on people's mental health has increased exponentially as a result of the growing usage of social media platforms, offering important new information for the diagnosis of mental illnesses. In order to identify possible mental health problems using social media data, this research investigates the use of Machine Learning (ML) methods, including Random Forest and Decision Tree algorithms. The technology looks at user-shared textual information to determine if a user may be dealing with a mental health issue based on their interactions and postings. Natural language processing (NLP) methods including tokenisation, stopword removal, and vectorisation utilising the Term Frequency-Inverse Document Frequency (TF-IDF) approach are used in this work to preprocess the textual data. Two popular classification models, Random Forest and Decision Tree, are then trained using the preprocessed data. While the Decision Tree algorithm creates a tree-like model to generate predictions based on feature values, the Random Forest algorithm, an ensemble learning technique, uses numerous decision trees to increase prediction accuracy and resilience. The classification accuracy of the trained models is assessed; the Random Forest model is anticipated to provide superior generalisation by minimising overfitting in contrast to the Decision Tree model. In order to ascertain if a user's postings suggest the possibility of mental health conditions like stress, anxiety, or depression, both models are evaluated using social media data. The findings of this research are intended to aid in the creation of automated instruments for early mental health identification, which may facilitate prompt assistance and intervention. To sum up, the use of machine learning algorithms like Random Forest and Decision Tree provide a viable method for identifying mental health conditions using social media data, demonstrating the promise of artificial intelligence in the medical field. This may help organisations and mental health experts provide people in need early support.