자질기반 감성분석 모델 학습을 위한 주석데이터셋 FeSAD 구축 방법론
A Methodology of Constructing Sentiment-Annotated Datasets for Training a FbSA model
0
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
This study introduces the process of constructing FeSAD (Feature-Sentiment-Annotated Dataset) based on the Semi-automatic Propagation methodology (SSP), which aims for Korean FbSA (Feature-based Sentiment Analysis). FeSAD was constructed by a 2-step annotation process: the SSP methodology is applied at the first step, and then human annotators revise the annotated results. The linguistic resources for SSP consist of the LGG (Local Grammar Graph) patterns and the DECO (Dictionnaire Electronique du COreen) Korean machine-readable dictionaries. In this study, we evaluated the performance of the SSP-based approach with Cosmetics and Food domain texts. The result shows 0.93 and 0.90 F1-score for each domain, which reveals that the SSP-based approach could reduce the amount of the human annotators' task under 10%.
Abstract
This study introduces the process of constructing FeSAD (Feature-Sentiment-Annotated Dataset) based on the Semi-automatic Propagation methodology (SSP), which aims for Korean FbSA (Feature-based Sentiment Analysis). FeSAD was constructed by a 2-step annotation process: the SSP methodology is applied at the first step, and then human annotators revise the annotated results. The linguistic resources for SSP consist of the LGG (Local Grammar Graph) patterns and the DECO (Dictionnaire Electronique du COreen) Korean machine-readable dictionaries. In this study, we evaluated the performance of the SSP-based approach with Cosmetics and Food domain texts. The result shows 0.93 and 0.90 F1-score for each domain, which reveals that the SSP-based approach could reduce the amount of the human annotators' task under 10%.
참고문헌 (30)
- 김문형, "KOSAC (Korean Sentiment Analysis Corpus): 한국어 감정 및 의견분석 코퍼스", 한국정보과학회 학술발표논문집, pp.650~652 (2013)
- 남지순, "오피니언 극성을 전환하는 한국어 부정표현 자동 인식을 위한 연구", 언어와언어학, (57), pp.61~94 (2012), 언어연구소
- 남지순, "코퍼스 분석을 위한 한국어 전자사전 구축 방법론" (2018), 도서출판 역락
- 남지순, "자질기반 감성분석(FbSA) 모델의 인공지능 학습을 위한 지식베이스ㆍ패턴문법 기반 반자동 학습데이터 증강(SSP) 방법 및 장치", DICORA-TR-2021-10. 한국외대 디코라연구센터, ~ (2021)
- 박상민, "Bi-LSTM 기반의 한국어 감성사전 구축 방안", 지능정보연구, 24(4), pp.219~240 (2018), 한국지능정보시스템학회
- 신동혁, "한국어 감성 사전 DecoSelex 구축을 위한 영어 SentiWordNet 활용 및 보완 논의", 한국사전학, (28), pp.75~111 (2016), 한국사전학회
- 안애림, "한국어 오피니언 문장 분류 시스템을 위한 사전 및 구문 패턴 연구", 석사, 언어인지과학, pp.2011
- 이도영, "온라인 텍스트종류로서의 상품평 연구 - 독일 아마존 온라인 쇼핑몰의 ‘마스크’ 상품평을 중심으로", 독일언어문학, (93), pp.53~73 (2021), 한국독일언어문학회
- 이상진, "책 리뷰 말뭉치를 활용한 형용사, 부사 감성 사전 개발", 언어과학연구, (92), pp.27~40 (2020), 언어과학회
- 이준환, "한국어 맛 평가 형용사에 관한 연구", 감성과학, 16(4), pp.493~502 (2013), 한국감성과학회[DOI]
- 조동희, "MUSE 감성주석코퍼스 구축을 위한 분류 체계 및 태그셋 연구", 우리말연구, (47), pp.5~47 (2016), 우리말학회
- 조수선, "온라인 신문 댓글의 내용분석: 댓글의 유형과 댓글 게시자의 성향", 커뮤니케이션학 연구, 15(2), pp.65~84 (2007), 한국커뮤니케이션학회
- 양철원, "기업 재무분석을 위한 한국어 감성사전 구축", 한국증권학회지, 50(2), pp.135~170 (2021), 한국증권학회[DOI]
- DecoLoTA, "황창회", 한국외대 디코라연구센터, ~, pp.DICORA-TR-2020-01 (2020)
- 황창회, "자질기반 감성분석을 위한 다단어표현 사전 DecoMWE 연구", 언어와 정보 사회, 35, pp.407~458 (2018), 언어정보연구소[DOI]
- Ahn, A., "Semantic Polarity of Adjectival Predicates in Online Reviews", ArXiv, abs, 2012
- Aragon, O. R., "Dimorphous Expressions of Positive Emotion : Displays of Both Care and Aggression in Response to Cute Stimuli", Psychological Science, 26, pp.259~273 (2015)
- Ataei, T. S., "Pars-ABSA: An Aspect-based Sentiment Analysis Dataset in Persian", ArXiv, abs, 2019 (1908)
- Blitzer, J., "Biographies, Bollywood, Boom-boxes and Blenders : Domain Adaptation for Sentiment Classification", Proceedings of the 45th Annual Meeting of the Association of Computational Linguistics, pp.440~447 (2007)
- Gross, M., "The Construction of Local Grammars. Finite-State Language Processing" (1997), the MIT Press
- Hyun, D., "Building Large-Scale English and Korean Datasets for Aspect-Level Sentiment Analysis in Automotive Domain", Proceedings of the 28th International Conference on Computational Linguistics, pp.961~966 (2020)
- Lei, Z., "Identifying Noun Product Features That Imply Opinions", Proceedings of the Annual Meeting of the Association for Computational Linguistics, pp.575~580 (2011)
- Liu, B., "Sentiment Analysis and Opinion Mining" (2012), Morgan and Claypool Publishers
- Mudalige, C. R., "SigmaLaw-ABSA: Dataset for Aspect-Based Sentiment Analysis in Legal Opinion Texts", 2020 IEEE 15th International Conference on Industrial and Information Systems (ICIIS), pp.488~493 (2020)
- Nam, J. -S., "A Novel Dichotomy of the Korean Adverb Nemwu in Opinion Classification", Studies in Language, 38(1), pp.171~209 (2014)
- Paumier, S., "Unitex Users’ Manual" (2003), UPEM
- Pontiki, M., "SemEval-2014 Task 4:Aspect Based Sentiment Analysis", Proceedings of the 8th International Workshop on Semantic Evaluation, pp.27~35 (2014)
- Ray, B., "An Ensemble-based Hotel Recommender System Using Sentiment Analysis and Aspect Categorization of Hotel Reviews", Applied Soft Computing, 98, pp.106935~ (2021)
- Song, M., "Attention-based Long Short-Term Memory Network Using Sentiment Lexicon", Information Processing and Management, 56(3), pp.637~653 (2019)
- Wiebe, J., "Annotating Expressions of Opinions and Emotions in Language", Language Resources and Evaluation, 39(2-3), pp.165~210 (2005)