스포츠 기사 댓글에서 수사의문문으로 표현된 풍자 표현의 자동인식
Identification of Sarcastic Expressions Using Rhetorical Question in Sports Articles.
0
조회
0
다운로드
2
인용
0
참고문헌
키워드
초록
This paper presents an experiment of automatic detection of Korean sarcastic expressions appeared in the comments of Korean sports articles. When sarcasm is expressed in text, its automatic detection becomes challenging since the accurate interpretation can be identified only by figuring out its underlying meaning. However, the sentences implying sarcasm can be detected utilizing a set of features which is selected considering the characteristics of the domain in question. This research focuses on identifying sarcastic meaning expressed in text of sports domain in which sarcasm is frequently expressed in the form of rhetorical question. In particular, a sentence final suffix‘nya’is adopted to construct rhetorical question expressing mostly negative sentiment although the suffix itself does not represent any sentiment at all. A set of relevant features including the suffix is selected from the data and classified. A series of experiments utilizing the classified features have proven that non-sentiment bearing words such as a function word or a suffix can be contributed to identify implicit sentiment, such as sarcasm.
Abstract
This paper presents an experiment of automatic detection of Korean sarcastic expressions appeared in the comments of Korean sports articles. When sarcasm is expressed in text, its automatic detection becomes challenging since the accurate interpretation can be identified only by figuring out its underlying meaning. However, the sentences implying sarcasm can be detected utilizing a set of features which is selected considering the characteristics of the domain in question. This research focuses on identifying sarcastic meaning expressed in text of sports domain in which sarcasm is frequently expressed in the form of rhetorical question. In particular, a sentence final suffix‘nya’is adopted to construct rhetorical question expressing mostly negative sentiment although the suffix itself does not represent any sentiment at all. A set of relevant features including the suffix is selected from the data and classified. A series of experiments utilizing the classified features have proven that non-sentiment bearing words such as a function word or a suffix can be contributed to identify implicit sentiment, such as sarcasm.
참고문헌 (19)
- 구현정, "의사소통의 기법" (2005), 박이정
- 국립국어원, "외국인을 위한 한국어 문법2" (2005), 커뮤니케이션북스
- 김순자, "여성 화자의 화행 수행에 관한 연구 : 동료들 사이의 대화를 중심으로", 박사, 국어국문학, pp.2001
- 윤경원, "한국어 혼잣말의 유형과 ‘-냐’ 혼잣말의 의사소통적 기능", 한국문법교육학회 학술발표논문집 (2010)
- "표준국어대사전" (2008)[URL]
- Bamman, David, "Contextualized Sarcasm Detection on Twitter", Proceedings of the Ninth International AAAI Conference on Web and Social Media (2015)
- Camp, Elisabeth, "Sarcasm, Pretense, and The Semantics", Pragmatics Distinction, 2012, pp.46(4), 587~634
- Colston, Herbert L., "The Routledge handbook of language and humor", pp.234~249 (2017), Routledge
- Hancock, Jeffrey T., "Verbal Irony Use in Face-To-Face and Computer-Mediated Conversations", Journal of Language and Social Psychology, 23(4), pp.447~463 (2004)
- Ivanko, Stacey L., "Context incongruity and irony processing", Discourse Processes, 35(3), pp.241~279 (2003)
- Joshi, Aditya, "Are word embedding-based features useful for sarcasm detection?", Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing (2016)
- Kumon-Nakamura, Sachi, "How About Another Piece Of Pie? The Allusional Pretense Theory Of Discourse Irony", Journal of Experimental Psychology: General, 124, pp.3~21 (1995)
- Maaten, Laurens van der, "Visualizing High-Dimensional Data Using t-SNE", Journal of Machine Learning Research, 9, pp.2579~2605 (2008)
- Pedregosa, Fabian, "Scikit-learn: Machine Learning in Python", JMLR, 12, pp.2825~2830 (2011)
- Roberts, Richard M., "Why do people use figurative language?", Psychological Science, 5(3), pp.159~163 (1994)
- Sadock, Jerrold, "Queclaratives", CLS, 7, pp.223~231 (1971)
- Tay, Yi, "Reasoning with Sarcasm by Reading In-between", Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Long Papers), pp.1010~1020 (2018)
- Wallace, Byron C., "Sparse, Contextually Informed Models for Irony Detection: Exploiting User Communities, Entities and Sentiment", Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing, pp.1035~1044 (2015)
- Zhang, Meishan, "Tweet Sarcasm Detection Using Deep Neural Network", Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers, pp.2449~2460 (2016)