An Intelligent Hybrid Framework For Classification Of Anxiety And Depression Using Data Augmentation

Abstract

Mental health problems are significant challenges for individuals or society as well. The impact of mental health disorders is a kind of slow poison that affects the country's growth substantially. The accurate and timely diagnosis of these disorders is crucial for effective intervention and treatment. The current research proposes an innovative Intelligent Hybrid Framework for the classification of mental health disorders such as depression and anxiety by utilizing advanced machine learning techniques and data augmentation. The proposed framework provides the classification of mental health disorders. It enhances the accuracy and robustness of the classification process with the involvement of synthetic data values generated from the existing dataset. The hybrid framework capitalizes on the strengths of different classifiers and incorporates ensemble learning principles to create a more resilient and reliable classification system. The outcomes indicate the classification of depressive diseases and normal text. The proposed model provides 99.1% accuracy of the system for the classification of data.