Exploring Author Context for Detecting Intended vs Perceived Sarcasm
This work addresses sarcasm detection for natural language processing applications, but it is incremental as it builds on existing methods with a focus on author context.
The study tackled sarcasm detection by using author context from historical Twitter posts, achieving state-of-the-art performance on a distantly supervised dataset but not on a manually labeled one, highlighting a distinction between intended and perceived sarcasm.
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.