Abstract

Sarcasm is a type of sentiment where people express negative sentiment using positive connotation words in text and vice-versa. In this work, we propose a cross-domain sarcasm detection framework that allows acquisition, storage and processing of tweets for detecting sarcastic content in online reviews. We conduct our experiments on Amazon product review dataset namely the Sarcasm Corpus Version1 having about 2000 reviews. We use Support Vector Machines (SVM) and Neural Networks (NN) for detecting sarcasm using lexical, pragmatic, linguistic incongruity and context incongruity features. We report the results and present a comparative evaluation of SVM and NN classifiers for single domain sarcasm detection indicating their suitability for the task. Then, we use these models for cross-domain sarcasm detection. The experimental results indicate the reliability of our approach.