Abstract
The figurative language involving sarcasm on social networks is evolving the way how the humans use computers to communicate. Consequently, artificial intelligence techniques are applied in various scenarios to make the social networking more intelligent - for instance, identification of figurative language. Identifying both literal and non-literal meaning is not easy for a machine and it is hard even for people. Therefore, novel and exact frameworks ready to identify figurative languages are important. In sarcasm detection, this is even more challenging because sarcasm changes the polarity of an evidently positive or negative expression into its inverse. To maintain a distance for a sarcastic message being comprehended in its unintended actual meaning, in micro-blogging sites, for example messages on Twitter, sarcasm is frequently set apart with a hashtag for example, '#sarcastic', '#sarcasm', '#not' etc. Moreover, the customer reviews may also contain some element of sarcasm. To contribute to this area, we gathered the data of tweets and reviews from Twitter, thesarcasmdetector.com , and Kaggle and proposed a mechanism for detecting sarcasm automatically using a classifier. A detailed experimental study was also conducted to evaluate the proposed mechanism. The results of this study were quite promising and proved the effectiveness of our approach.