Harnessing Context Incongruity for Sarcasm Detection

The relationship between context incongruity and sarcasm has been studied in linguistics. We present a computational system that harnesses context incongruity as a basis for sarcasm detection. Our statistical sarcasm classifiers incorporate two kinds of incongruity features: explicit and implicit. We show the benefit of our incongruity features for two text forms - tweets and discussion forum posts. Our system also outperforms two past works (with Fscore improvement of 10-20%). We also show how our features can capture intersentential incongruity.

• Type: Journal
• Year: 2015
• Where: ACL
• Authors: Aditya Joshi, Vinita Sharma, Pushpak Bhattacharyya
• Keywords: ACL 2015, Computational Linguistics