지진 관련 SNS 텍스트에 나타난 비명시적 감성표현 연구
A Study of Implicit Sentiment Expressions in Earthquake-Related Social Media Texts
0
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
This paper studies domain-dependent implicit sentiment expressions in earthquake-related social media texts. In sentiment analysis, domain-dependent implicit sentiment expressions are difficult to estimate and recognize, which often results in the depreciation of system performance. In this study, we analyzed two types of implicit sentiment expressions that may occur in the causal clause of the sentence conveying ‘fear’ sentiment: {simple predicate} type such as ‘collapse’ and {complex predicate} such as ‘blow up’. When these clauses appear without main clauses that express explicit sentiments such as ‘anxiety’ or ‘panic’, they imply the omitted sentiment and thus implicitly express certain sentiments by themselves. The DECO T-Crawler platform was used to collect earthquake-related data in social media texts and the DECO Korean dictionary and local-grammar graph formalism were used to the corpus. The performance of resources built in this study showed 84.5% accuracy in a test corpus, which is about 23% higher than the accuracy expected when using only sentiment-conveying words.
Abstract
This paper studies domain-dependent implicit sentiment expressions in earthquake-related social media texts. In sentiment analysis, domain-dependent implicit sentiment expressions are difficult to estimate and recognize, which often results in the depreciation of system performance. In this study, we analyzed two types of implicit sentiment expressions that may occur in the causal clause of the sentence conveying ‘fear’ sentiment: {simple predicate} type such as ‘collapse’ and {complex predicate} such as ‘blow up’. When these clauses appear without main clauses that express explicit sentiments such as ‘anxiety’ or ‘panic’, they imply the omitted sentiment and thus implicitly express certain sentiments by themselves. The DECO T-Crawler platform was used to collect earthquake-related data in social media texts and the DECO Korean dictionary and local-grammar graph formalism were used to the corpus. The performance of resources built in this study showed 84.5% accuracy in a test corpus, which is about 23% higher than the accuracy expected when using only sentiment-conveying words.
참고문헌 (14)
- 김은미, "뉴스 미디어로서의 트위터: 뉴스 의제와 뉴스에 대한 대화를 중심으로", 한국언론학보, 55(6), pp.152~180 (2011), 한국언론학회
- 남지순, "코퍼스 분석을 위한 한국어 전자사전 구축방법론" (2018), 도서출판 역락
- 배병걸⋅이보람⋅최선화, "소셜 빅데이터와 지진의 연관성 분석", 한국정보과학회 학술발표논문집, pp.13~15 (2015), 한국정보과학회
- 서민송, "재난 관련 트윗 데이터 분석에 의한 시민 감성도 평가", 대한공간정보학회지, 26(3), pp.41~50 (2018), 대한공간정보학회[DOI]
- Blitzer, J., "Biographies, bollywood, boom-boxes and blenders: Domain adaptation for sentiment classification", ACL, 7, pp.440~447 (2007)
- Gross, M., "Finite-State Language Processing", pp.329~354 (1997), MIT Press
- Gross, M., "A bootstrap method for constructing local grammars", Proceedings of the Symposium on Contemporary Mathematics, pp.229~250 (1999), University of Belgrade
- Deco Crawlers DECO TR-2018-01, DICORA, "Hwang, C.", Hankuk University of Foreign Studies, ~ (2018)
- Nam, J., "A novel dichotomy of the Korean adverb nemwu in opinion classification", Studies in Language, 38(1), pp.169~207 (2014)
- Korean Electronic Dictionary DECO TR-2015-02, DICORA, "Nam, J.", Hankuk University of Foreign Studies, ~ (2015)
- Pang, B., "Opinion mining and sentiment analysis", Foundations and trends in information retrieval, 2(1-2), pp.1~135 (2008)
- Paumier, S., "De la reconnaissance de formes linguistiques a l’analyse syntaxique", Ph.D., pp.2003
- Vo, B., "Twitter emotion analysis in earthquake situations", International Journal of Computational Linguistics and Applications, 4(1), pp.159~173 (2013)
- DecoTex users’ mannual DECO TR-2017-12, DICORA, "Yoo, G.", Hankuk University of Foreign Studies, ~ (2017)