Irony detection in Twitter with imbalanced class distributions

Abstract

Irony detection is a not trivial problem and can help to improve natural language processing tasks as sentiment analysis. When dealing with social media data in real scenarios, an important issue to address is data skew, i.e. the imbalance between available ironic and non-ironic samples available. In this work, the main objective is to address irony detection in Twitter considering various degrees of imbalanced distribution between classes. We rely on the emotIDM irony detection model. We evaluated it against both benchmark corpora and skewed Twitter datasets collected to simulate a realistic distribution of ironic tweets. We carry out a set of classification experiments aimed to determine the impact of class imbalance on detecting irony, and we evaluate the performance of irony detection when different scenarios are considered. We experiment with a set of classifiers applying class imbalance techniques to compensate class distribution. Our results indicate that by using such techniques, it is possible to improve the performance of irony detection in imbalanced class scenarios.