Visual Emotion Analysis for Depression Detection on Social Media: A Review

Depression continues to be one of the most prevalent mental health challenges, affecting millions of individuals across the globe. Early identification is crucial for ensuring timely intervention and psychological support. In recent years, the widespread use of social media has opened up new avenues for understanding user behaviour and emotional patterns. These digital platforms, when analysed using artificial intelligence (AI) techniques, offer promising potential in detecting early signs of depression. While earlier research primarily focused on analysing textual content from social media, recent progress in computer vision has enabled the exploration of visual data—particularly facial expressions, body posture, and image content—for depression detection. This review paper presents a comprehensive overview of image-based approaches, with an emphasis on the application of machine learning (ML) and deep learning (DL) models. It further discusses popular methodologies, standard benchmark datasets, commonly used evaluation metrics, and prevailing challenges in this growing area of research. The paper concludes by outlining potential future directions, including multi-modal data fusion, ethical implications, and the scope for real-world implementation.