JSAI2019

Presentation information

International Session

International Session » [ES] E-2 Machine learning

[2A4-E-2] Machine learning: method extensions

Wed. Jun 5, 2019 3:20 PM - 5:00 PM Room A (2F Main hall A)

Chair: Junichiro Mori (The University of Tokyo)

The room is connected with B.

4:00 PM - 4:20 PM

[2A4-E-2-03] Exploring Machine Learning Techniques for Irony Detection

〇Zheng Lin Chia1, Michal Ptaszynski1, Fumito Masui1 (1. Kitami Institute of Technology)

Keywords:Irony Detection

Irony detection is considered a complex task in Natural Language Processing. This paper first introduce and cover the recently state of irony detection. Then we review and summarize previous related research on text-based irony detection. Finally we compare various classifiers including the proposed CNN model on three dataset of tweets, and analysis and discuss the results. We conclude that CNN is effective for irony detection under various situation with our model outperforming all the other classifiers.