Predictive Modeling of Mental Health Awareness Using Naive Bayes Algorithm

This research explores predictive modeling of mental health awareness using the Naive Bayes algorithm, focusing on personal and social factors such as age, gender, stress levels, prior mental health issues, and social support. The dataset underwent preprocessing to handle missing values and encode categorical variables, followed by feature selection to identify the most influential predictors. The model was trained on a split dataset to predict awareness levels, with evaluation metrics confirming its accuracy and reliability. Key findings revealed the significant relationship between stress levels, social support, and prior mental health experiences on awareness, offering actionable insights for targeted interventions. This study highlights the potential of data-driven approaches to enhance mental health awareness and guide effective outreach programs.