Decoding emotions: Leveraging machine learning to analyze emotional expression for deeper mental health insights

Abstract

The increasing frequency of mental health illnesses, their multiple symptoms, and complications with other conditions bring complexity to diagnosis and increase the risk of misdiag-nosis. This research emphasizes the growing need for healthcare practitioners to evaluate patients' mental health memories for more effective therapy. The World Health Organization's (WHO) research underlines the severity of mental health problems as a major contributor to suicide, particularly affecting the young population. Stress, frequently unrecognized, can have negative repercussions, needing early identification and intervention. With mental health disorders known as a substantial contributor to sui-cide, early detection is vital. Early identification of mental health disorders, is essential to prevent the worst outcome, decrease the risk of suicide, boost the effectiveness of therapy, improve overall well-being, and provide cost-efficient therapies. Therefore, leveraging automated classifiers, including SVM, BERT, Random Forest, Logistic Regression, and a Proposed CNN model, the study evaluates emotional expression in online posts by cancer patients. The Proposed CNN model surpasses existing classifiers in classification and sentiment analysis with an accuracy of 89.12%, emphasizing the transformative potential of machine learning (ML) in mental health research for early identification and improving the treatment process.