Exploring Author Context for Detecting Intended vs Perceived Sarcasm

TL;DR

This paper explores how incorporating author historical context improves sarcasm detection in tweets, highlighting differences between intended and perceived sarcasm through neural models and diverse datasets.

Contribution

It introduces neural models that utilize author context for sarcasm detection and compares performance on datasets with different labeling methods.

Findings

State-of-the-art results on distant supervision dataset

Limited improvement on manually labeled dataset

Highlights difference between intended and perceived sarcasm

Abstract

We investigate the impact of using author context on textual sarcasm detection. We define author context as the embedded representation of their historical posts on Twitter and suggest neural models that extract these representations. We experiment with two tweet datasets, one labelled manually for sarcasm, and the other via tag-based distant supervision. We achieve state-of-the-art performance on the second dataset, but not on the one labelled manually, indicating a difference between intended sarcasm, captured by distant supervision, and perceived sarcasm, captured by manual labelling.