Skip to main content

Research Repository

See what's under the surface

Advanced Search

Sarcasm detection on Czech and English Twitter

Ptácek, Tomás; Habernal, Ivan; Hong, Jun

Authors

Tomás Ptácek

Ivan Habernal

Jun Hong Jun.Hong@uwe.ac.uk
Professor in Artificial Intelligence



Abstract

This paper presents a machine learning approach to sarcasm detection on Twitter in two languages – English and Czech. Although there has been some research in sarcasm detection in languages other than English (e.g., Dutch, Italian, and Brazilian Portuguese), our work is the first attempt at sarcasm detection in the Czech language. We created a large Czech Twitter corpus consisting of 7,000 manually-labeled tweets and provide it to the community. We evaluate two classifiers with various combinations of features on both the Czech and English datasets. Furthermore, we tackle the issues of rich Czech morphology by examining different preprocessing techniques. Experiments show that our language-independent approach significantly outperforms adapted state-of-the-art methods in English (F-measure 0.947) and also represents a strong baseline for further research in Czech (F-measure 0.582).

Presentation Conference Type Conference Paper (unpublished)
Start Date Aug 23, 2014
Publication Date Aug 23, 2014
Peer Reviewed Peer Reviewed
Pages 213-223
APA6 Citation Ptácek, T., Habernal, I., & Hong, J. (2014, August). Sarcasm detection on Czech and English Twitter. Paper presented at COLING 2014
Keywords sarcasm, detection, Czech, English, Twitter
Publisher URL http://anthology.aclweb.org/C/C14/
Additional Information Title of Conference or Conference Proceedings : Proceedings of COLING 2014, the 25th International Conference on Computational Linguistics
;