Identifying suicidal ideation on Twitter is crucial for timely intervention and suicide prevention efforts. This study leverages Twitter data to identify individuals contemplating suicide, addressing the challenge of distinguishing genuine suicidal ideations from those posted for entertainment. Given the rise in depression and anxiety, particularly among the youth, an ensemble model combining various machine learning algorithms is proposed to enhance the accuracy of detecting genuine suicidal tweets. The ensemble model integrates the predictions of multiple internal models: Logistic Regression, LinearSVC, XGBoost, Naive Bayes, and Random Forest. Each model generates a prediction based on extracted features from the tweets, and the final prediction is determined by calculating the weighted average of these predictions, considering the relative importance of each model. If this weighted average exceeds a predefined threshold, the tweet is classified as non-suicidal; otherwise, it is classified as suicidal. This methodology allows the ensemble model to balance the strengths and weaknesses of individual models, resulting in a robust and accurate classifier. Incorporating BERT classification and VADER sentiment analysis, the model is trained on labeled data to capture intricate patterns in tweet embeddings. Evaluated against various performance metrics, the ensemble model achieves an accuracy of 95.81%, precision of 93.45%, recall of 89.90%, and an F1-score of 94.68%, significantly outperforming individual models. The model also demonstrates a superior AUC-ROC value of 0.95, indicating excellent performance in distinguishing between classes. This approach not only advances the current methodologies but also contributes to public health by enhancing the reliability of suicide prevention efforts on social media platforms. 

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.