People often share their thoughts and feelings with friends and family on social media, providing valuable insights into their mental state. Recognizing the importance of this, recent studies in NLP and psychology have focused on identifying suicidal thoughts through the analysis of online social network activity. By effectively utilizing Data from social media platforms, coupled with the intricate early indicators of suicidal ideation, can be identified, potentially averting numerous fatalities. This research delves into the application of machine learning and deep learning techniques for the detection of suicide intent across platforms such as Twitter, WhatsApp, and Facebook.. The principal objective is to improve the performance of the model in surpassing the outcomes of preceding studies, thereby more precisely detecting early warning indicators and averting suicide attempts. This is accomplished through the integration of deep learning and machine learning models with feature extraction techniques such as word embedding and count vectorizer.