한국어 감정분석 코퍼스를 활용한 양상정보 기반의 감정분석 연구
Modality-based Sentiment Analysis through the Utilization of the Korean Sentiment Analysis Corpus
2
조회
0
다운로드
22
인용
0
참고문헌
키워드
초록
This study develops a practical application of language resources from the Korean Sentiment Analysis Corpus (KOSAC) for sentiment analysis research. With this in mind, based on their sentiment properties and the probabilistic factors of annotated expressions from KOSAC, we extracted annotated expressions and refined them to be a sentiment analysis research resource. This study attempted to break away from simple calculation methods dependant on the distribution of lexical polarity items seen in previous research. Additionally, in order to perform more sophisticated sentiment analysis, we attempted to introduce pragmatic information which includes modality. In order to achieve this, we cataloged expressions that include pragmatic information related to the speaker's attitude, based on their relative probability in KOSAC. After doing so, this study shows a practical application of this new language resource to subjectivity analysis research. When using this new resource, this research demonstrates an accuracy improvement of around 6%. This demonstrates very clearly that, in addition to polarity items, there exists a need to include a variety of aspects and lexical information when doing this type of research. Moreover, this extraction of sentiment expressions, depending on their semantic and pragmatic properties, not only shows an additional use of KOSAC, but also establishes a new resource in the field of sentiment analysis.
Abstract
This study develops a practical application of language resources from the Korean Sentiment Analysis Corpus (KOSAC) for sentiment analysis research. With this in mind, based on their sentiment properties and the probabilistic factors of annotated expressions from KOSAC, we extracted annotated expressions and refined them to be a sentiment analysis research resource. This study attempted to break away from simple calculation methods dependant on the distribution of lexical polarity items seen in previous research. Additionally, in order to perform more sophisticated sentiment analysis, we attempted to introduce pragmatic information which includes modality. In order to achieve this, we cataloged expressions that include pragmatic information related to the speaker's attitude, based on their relative probability in KOSAC. After doing so, this study shows a practical application of this new language resource to subjectivity analysis research. When using this new resource, this research demonstrates an accuracy improvement of around 6%. This demonstrates very clearly that, in addition to polarity items, there exists a need to include a variety of aspects and lexical information when doing this type of research. Moreover, this extraction of sentiment expressions, depending on their semantic and pragmatic properties, not only shows an additional use of KOSAC, but also establishes a new resource in the field of sentiment analysis.
참고문헌 (27)
- 김문형, "KOSAC(Korean Sentiment Analysis Corpus): 한국어 감정 및 의견 분석 코퍼스", 2013년 한국컴퓨터종합학술대회 논문집 (2013)
- Banfield, Ann, "Unspeakable Sentences" (1982), Routledge and Kegan Paul
- Bergler, Sabine, "Evidential Analysis or Reported Speech", Ph.D, pp.1992
- Chafe, Wallace, "Evidentiality: The Linguistic Coding of Epistemology" (1986), Ablex
- Choi, Yejin, "Identifying Sources of Opinions with Conditional Random Fields and Extraction Patterns", Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing (HLT, 2005, ~
- Cortes, Corinna, "Support-Vector Networks", Machine Learning, 20, pp.273~297 (1995)
- Fan, Rong-En, "LIBLINEAR: A Library for Large Linear Classification", Journal of Machine Learning Research, 9, pp.1871~1874 (2008)
- Finegan, Edward, "Subjectivity and subjectification: an introduction, in D. Stein & S. Wright (eds), Some observations on factivity", Papers in Linguistics, 47, pp.340~358 (1995)
- Karttunen, Lauri, "Presuppositions of compound sentences", Linguistic Inquiry, 4(2), pp.169~193 (1973)
- Kim, Munhyong, "Pinpointing Sentence-Level Subjectivity through Balanced Subjective and Objective Features", Lecture Notes in Artificial Intelligence, 8686 (2014)
- "Korean Sentiment Analysis Corpus" (2012)[URL]
- Langacker, Ronald, "Iconicity in Syntax. Typological Studies in Language 6" (1985), John Benjamins
- Langacker, Ronald, "Foundations of Cognitive Grammar, vol. 2, DescriptiveApplication" (1991), Stanford University Press
- Langacker, Ronald, "Language and Conceptualization", pp.229~252 (1997), Cambridge University Press
- "Multi-Perspective Question Answering" (2005)[URL]
- Mushin, Llana, "Evidentiality and Epistemological Stance" (2001), John Benjamins
- Palmer, Frank, "Mood and Modality" (1986), Cambridge University Press
- Pustejovsky, James, "The TimeBank corpus", Proceedings of Corpus Linguistics 2003, pp.647~656 (2003)
- Riloff, Ellen, "Learning Extraction Patterns for Subjective Expressions", Conference on Empirical Methods in Natural Language Processing (EMNLP-03), ACL-SIGDAT (2003)
- Riloff, Ellen, "Exploiting subjectivity classification to improve information extraction", Proceedings of the 20th National Conference on Artificial Intelligence (AAAI-2005), pp.1106~1111 (2005)
- Rubin, Victoria, "Epistemic modality: from uncertainty to certainty in the context of information seeking as interactions with texts", Information Processing and Management, 46, pp.533~540 (2010)
- Sauri, Roger, "A Factuality Profiler for Eventualities in Text", Ph.D, pp.2008
- Sauri, Roger, "Determining modality and factuality for text entailment", Proceedings of the First IEEE International Conference on Semantics Computing, pp.509~516 (2007)
- Shin, Hyopil, "Annotation Scheme for Constructing Sentiment Corpus in Korean", Proceedings of the 26th Pacific Asia Conference on Language, Information and Computation, pp.181~190 (2012)
- 신효필, "A Corpus Study of Nested Sources for Subjectivity Analysis", 언어학, (69), pp.67~87 (2014), 사단법인 한국언어학회
- Instructions for annotating opinions in newspaper articles, "Wiebe, Janyce", University of Pittsburgh, ~, pp.Department of Computer Science Technical Report TR-02-101 (2002)
- Wiebe, Janyce, "Annotating expressions of opinions and emotions in Language", Language Resources and Evaluations, 39(2), pp.165~210 (2005)