A Review on Sarcasm Detection from Machine-Learning Perspective

In this paper, we want to review one of the challengingproblems for the opinion mining task, which is sarcasm detection. To be able to do that, many researchers tried to explore suchproperties in sarcasm like theories of sarcasm, syntacticalproperties, psycholinguistic of sarcasm, lexical feature, semanticproperties, etc. Studies done in the last 15 years not only madeprogress in semantic features, but also show increasing amount ofmethod of analysis using a machine-learning approach to processdata. Because of this reason, this paper will try to explain currentmostly used method to detect sarcasm. Lastly, we will present aresult of our finding, which might help other researchers to gaina better result in the future.