DESIGN AND IMPLEMENTATION OF AN EDUCATIONAL MULTI-PLATFORM AWARENESS CAMPAIGN: TARGETING DEPRESSION USING BULK SMS

ABSTRACT This study investigates mental health awareness and education, focusing on understanding their impact on knowledge, attitudes, and behaviors related to mental health, especially among young people and educational settings. Mental health awareness involves spreading accurate information about mental disorders, symptoms, and treatments, while education teaches coping strategies and emotional resilience. Despite growing public attention, gaps remain in effective education methods and stigma reduction. The research employs a mixed-methods approach, combining quantitative machine learning models to classify awareness levels with qualitative thematic analysis to explore social and cultural barriers. Data were collected from university students through surveys and interviews. Results show that decision tree and support vector machine models classify mental health awareness with accuracies of 78.4 and 81.2 percent respectively, while an ensemble model improved accuracy to 84.5 percent. The main classification challenges arose in differentiating low and moderate awareness levels. Qualitative findings reveal stigma, cultural beliefs, and educational gaps as key obstacles to mental health understanding. These insights emphasize the need for integrated data-driven and culturally sensitive educational programs. The study concludes that machine learning can support mental health literacy assessment, but richer data and mixed-methods integration are essential for improving interventions. Recommendations include enhancing data collection, applying advanced modeling techniques, and developing targeted, community-informed education to promote early intervention and mental well-being. This research contributes to mental health scholarship by offering updated evidence on awareness efforts and proposing practical solutions to reduce stigma and improve public understanding.