• DOI:10.18653/v1/D16-1104
• Corpus ID: 5094895

Are Word Embedding-based Features Useful for Sarcasm Detection?

@inproceedings{Joshi2016AreWE,
  title={Are Word Embedding-based Features Useful for Sarcasm Detection?},
  author={Aditya Joshi and Vaibhav Tripathi and Kevin Patel and Pushpak Bhattacharyya and Mark James Carman},
  booktitle={EMNLP},
  year={2016}
}

• Aditya Joshi, Vaibhav Tripathi, +2 authors Mark James Carman
• Published in EMNLP 4 October 2016
• Computer Science

This paper makes a simple increment to state-of-the-art in sarcasm detection research. Existing approaches are unable to capture subtle forms of context incongruity which lies at the heart of sarcasm. We explore if prior work can be enhanced using semantic similarity/discordance between word embeddings. We augment word embedding-based features to four feature sets reported in the past. We also experiment with four types of word embeddings. We observe an improvement in sarcasm detection, irrespective of the word embedding used or the original feature set to which our features are augmented. For example, this augmentation results in an improvement in F-score of around 4\% for three out of these four feature sets, and a minor degradation in case of the fourth, when Word2Vec embeddings are used. Finally, a comparison of the four embeddings shows that Word2Vec and dependency weight-based features outperform LSA and GloVe, in terms of their benefit to sarcasm detection.