Due to the popularity of social media like Facebook, Twitter, WhatsApp, most people can share their opinions about other people without any social dishonors. This can lead to people being depressed. Furthermore, sarcastic words have a significant impact on depression levels. As a result, early depression detection is critical. Despite the fact that depression detection algorithms such as SVC, NB, DT, and LR have been developed using text data. However, there is scope for improvement. The proposed method for effectively detecting sarcasm is referred to as “Sarcastic News Dataset and Tweet-based Depression Detection (SNTDD)”. The proposed method for detecting sarcasm in text data uses machine-learning (ML) and deep-learning (DL) methods to obtain the sarcastic statements. The proposed model gives better accuracy and F1 score. The significance of this is that more positive indicates it has a stronger impact on mental health or raises the amount of depression. Sarcasm in study can be difficult to identify as a result of the complex relationship of text. In contrast to signs such as tone or facial expressions, NLP addresses a challenge of detecting sarcasm with requiring the use of context markers. In contrast to signs such as tone or facial expressions, NLP addresses the difficulty of detecting sarcasm. The experimental results reveal that the suggested model SNTDD is tested on the data and hybrid models. The model outperforms DL and ML on the news headline dataset, with an accuracy of 97.4% and received a 94.4% F1 score.