Social media platforms serve as avenues for individuals to express themselves and share pertinent details concerning their mental well-being through posts and comments. However, many individuals tend to overlook their mental health. This data lends itself to insightful analysis of an individual's psychological state through sentiment analysis techniques. The research explores the utilization of sentiment analysis techniques on social media data, specifically focusing on mental health discussions. Data gathered from platforms like Twitter is preprocessed and then used to train various Transformer models including DistilBERT, Albert, and a hybrid BERT-CNN model. Notably, the BERT-CNN hybrid model achieved a remarkable accuracy of 95%. This outcome underscores the effectiveness of advanced model architectures in analyzing mental health-related sentiment on social media. The significance of this research lies in its potential to offer valuable insights into individuals' mental states through computational analysis of their online expressions. The study's thorough methodology, encompassing data collection, preprocessing, and model training, sets a strong precedent for future research in this domain. Additionally, the successful performance of the BERT-CNN hybrid model highlights the importance of innovative model design in achieving accurate sentiment analysis results. Overall, this research contributes to the growing body of knowledge aimed at leveraging technology for mental health awareness and support.