Combining Humor and Sarcasm for Improving Political Parody Detection

TL;DR

This paper introduces a multi-encoder model that combines humor and sarcasm cues to enhance the detection of political parody tweets, outperforming previous methods.

Contribution

It proposes a novel multi-encoder architecture that jointly models humor and sarcasm for improved parody detection in social media texts.

Findings

Outperforms previous state-of-the-art methods

Effectively captures humor and sarcasm cues

Enhances political parody detection accuracy

Abstract

Parody is a figurative device used for mimicking entities for comedic or critical purposes. Parody is intentionally humorous and often involves sarcasm. This paper explores jointly modelling these figurative tropes with the goal of improving performance of political parody detection in tweets. To this end, we present a multi-encoder model that combines three parallel encoders to enrich parody-specific representations with humor and sarcasm information. Experiments on a publicly available data set of political parody tweets demonstrate that our approach outperforms previous state-of-the-art methods.