Sarcasm detection plays an important role in Natural Language Processing as it has been considered one of the most challenging task in sentiment analysis and opinion mining appli- cations. Our work aims to recognize sarcasm in social media sites, microblogs and discussion forums, exploiting the potential of Deep Learning tools such as Deep Neural Network and Word Embeddings. In this thesis, we (a) develop multiple types of neural models and and analyze their efficiency when combined with word embeddings; (b) create a new multitasking frame- work that exploits the strong correlation between sarcasm and sentiment detection (c) test the performances of our models on two pre-labelled datasets; (d) compare our results with other state-of-the-art models; (e) apply our models on real word data to evaluate the efficiency of their prediction.