ETRI-Knowledge Sharing Plaform

ENGLISH

성과물

논문 검색
구분 SCI
연도 ~ 키워드

상세정보

학술대회 A Generate-and-Test Method of Detecting Negative-Sentiment Sentences
Cited 0 time in scopus Download 0 time Share share facebook twitter linkedin kakaostory
저자
최윤정, 오효정, 맹성현
발행일
201203
출처
International Conference on Intelligent Text Processing and Computational Linguistics (CICling) 2012 (LNCS 7181), v.7181, pp.500-512
DOI
https://dx.doi.org/10.1007/978-3-642-28604-9_41
협약과제
11VS1200, 웹 인텔리전스를 위한 웹 폭증 데이터 분석형 리스닝 플랫폼용 소셜웹 이슈탐지-모니터링 및 예측원천 기술, 김현기
초록
Sentiment analysis requires human efforts to construct clue lexicons and/or annotations for machine learning, which are considered domain-dependent. This paper presents a sentiment analysis method where clues are learned automatically with a minimum training data at a sentence level. The main strategy is to learn and weight sentiment-revealing clues by first generating a maximal set of candidates from the annotated sentences for maximum recall and learning a classifier using linguistically-motivated composite features at a later stage for higher precision. The proposed method is geared toward detecting negative sentiment sentences as they are not appropriate for suggesting contextual ads. We show how clue-based sentiment analysis can be done without having to assume availability of a separately constructed clue lexicon. Our experimental work with both Korean and English news corpora shows that the proposed method outperforms word-feature based SVM classifiers. The result is especially encouraging because this relatively simple method can be used for documents in new domains and time periods for which sentiment clues may vary. © 2012 Springer-Verlag.
KSP 제안 키워드
Analysis method, Domain-dependent, Experimental work, News corpora, SVM Classifier, machine Learning, sentiment analysis, simple method, training data