세분화된 한국어 감정 온톨로지 KoFiGEmOnto의 구축과 응용
KoFiGEmOnto,a Korean Fine-Grained Emotion Ontology - Its Construction and Application -
2
조회
0
다운로드
3
인용
0
참고문헌
키워드
초록
Since a decade, Text-Driven Emotion Processing has improved greatly, and is widely adopted in Opinion Mining or Sentiment Analysis. Based on coarse-grained classification, these sub-fields use only a couple of emotion features (2∼6) so far, and need to enlarge their success to more fined-grained emotion processing. In order to apply (semi-)automatic processing, the prerequisite is the construction of an enriched ontology in quality and quantity for every target language. This study reports in detail the construction of KoFiGEmOnto, a Korean Fine-Grained Emotion Ontology, for this purpose. In our previous studies, we have conducted component analysis of emotions and sophisticate criteria were dressed for building emotion ontology. Our raw corpus (about 22,000 utterances) was composed of 3 different kinds of texts, i.e. emojis, SMS texts, and film scripts.After careful analysis according to the proposed criteria, the first version of KoFiGEmOnto (approximately 11,300 unique types of emotional expressions) was constructed. We expect that KoFiGEmOnto will serve as a seed ontology for Korean fine-grained emotion processing.
Abstract
Since a decade, Text-Driven Emotion Processing has improved greatly, and is widely adopted in Opinion Mining or Sentiment Analysis. Based on coarse-grained classification, these sub-fields use only a couple of emotion features (2∼6) so far, and need to enlarge their success to more fined-grained emotion processing. In order to apply (semi-)automatic processing, the prerequisite is the construction of an enriched ontology in quality and quantity for every target language. This study reports in detail the construction of KoFiGEmOnto, a Korean Fine-Grained Emotion Ontology, for this purpose. In our previous studies, we have conducted component analysis of emotions and sophisticate criteria were dressed for building emotion ontology. Our raw corpus (about 22,000 utterances) was composed of 3 different kinds of texts, i.e. emojis, SMS texts, and film scripts.After careful analysis according to the proposed criteria, the first version of KoFiGEmOnto (approximately 11,300 unique types of emotional expressions) was constructed. We expect that KoFiGEmOnto will serve as a seed ontology for Korean fine-grained emotion processing.
참고문헌 (54)
- 김다해, "도메인 별 감성 분석을 위한 도메인 맞춤형 감성사전 구축 기법", 한국컴퓨터정보학회 학술발표논문집, 23(1), pp.15~18 (2015), 한국컴퓨터정보학회
- 김수연, "한글 감성 분류를 위한 감성 사전 구축에 관한 실험적 연구", 한국도서관정보학회 동계 학술발표자료집, pp.143~150 (2015), 한국도서관정보학회
- 김유영, "영화 리뷰 감성분석을 위한텍스트 마이닝 기반 감성 분류기 구축", 지능정보연구, 22(3), pp.71~89 (2016), 한국지능정보시스템학회[DOI]
- 박수진, "얼굴의 물리적 특징 분석 및 얼굴 관련 감성 어휘 분석 - 20대 한국인 여성 얼굴을 대상으로 -", 인지과학, 13(3), pp.1~10 (2002), 한국인지과학회
- 안정국, "집단지성을 이용한 한글 감성어 사전 구축", 지능정보연구, 21(2), pp.49~67 (2015), 한국지능정보시스템학회
- 유현경, "한국어 감정용언에 대한 연구", 한국사전학회 제33차 전국학술대회 학술발표논문집, pp.65~82 (2018), 한국사전학회
- 윤애선, "세분화된 한국어 감정 온톨로지 KoFiGEmOnto의 구축과 응용", 한국사전학회 제33차 전국학술대회 학술발표논문집, pp.87~113 (2018), 한국사전학회
- 윤애선, "감정 온톨로지의 구축을 위한 구성요소 분석", 인지과학, 21(1), pp.157~175 (2010), 한국인지과학회[DOI]
- 이상훈, "영역별 맞춤형 감성사전 구축을 통한 영화리뷰 감성분석", 지능정보연구, 22(2), pp.97~113 (2016), 한국지능정보시스템학회
- 이영민, "한국어 장소 리뷰를 이용한 공간 감성어 사전 구축 방법", 대한공간정보학회지, 25(2), pp.3~12 (2017), 대한공간정보학회[DOI]
- 이창환, "언어적 특성을 이용한 '심리학적 한국어 글분석 프로그램(KLIWC)'의 개발과정에 대한 고찰", 인지과학, 16(2), pp.93~121 (2005), 한국인지과학회
- 정영희, "기계학습 기반의 한국어 단문 감정분류 기법에 관한 연구", 박사, pp.2017
- 황재원, "감정 단어의 의미적 특성을 반영한 한국어 문서 감정분류 시스템", 정보과학회논문지 : 소프트웨어 및 응용, 37(4), pp.317~322 (2010), 한국정보과학회
- Adis, F., "Designing emotion of characters by referencing from facs in short animated film “RANA”", ejournals.umn.ac.id, 10(2), pp.31~38 (2017)
- Ballmer, Th., "Speech act classification" (1981), Spring-Verlag
- Birdwhistell, RL., "Communication in face to face interaction" (1972), Penquin
- Brooks, M., "Statistical affect detection in collaborative chat", Proceedings of the 2013 conference on Computer supported cooperative work (ACM), pp.317~328 (2013)
- Bruyne (de), L., "LT3 at SemEval-2018 Task 1: A classifier chain to detect emotions in tweets", Proceedings of the 12th International Workshop on Semantic Evaluation (SemEval-2018), pp.123~127 (2018)
- Calvo, R. A., "Emotions in text: Dimensional and categorical models", Computational Intelligence, 29(3), pp.527~543 (2013)
- Chaumartin, F. R., "UPAR7: A knowledge-based system for headline sentiment tagging", Proceedings of the Fourth International Workshop on Semantic Evaluations (SemEval-2007), pp.422~425 (2007)
- Ekman, P., "Emotions and life: Perspectives form psychology, biology, and evolution", American Psychological Association, ~ (2002)
- Esuli, A., "SentiWordNet: A publicly available lexical resource for opinion mining", Proceedings of the 5th Conference on Language Resources and Evaluation (LREC’06), pp.417~422 (2006)
- Fang, X., "Text sentiment analysis based on multi-granularity joint solution", Proceedings of the 3rd IEEE International Conference on Cloud Computing and Big Data Analysis, pp.315~321 (2018)
- Gui1, L., "Event-driven emotion cause extraction with corpus construction", Proceedings of the 2016Conference on Empirical Methods in Natural Language Processing, pp.1639~1649 (2016)
- Hasan, M., "EMOTEX: Detecting emotions in Twitter messages", 2014 ASE BIGDATA, CYBERSECURITY Conference, pp.2014[DOI]
- Jakobson, R., "Essais de linguistique générale" (1963), Les Éditions de Minuit
- Mohammad, S. M., "Emotion intensities in tweets", Proceedings of the 6th Joint Conference on Lexical and Computational Semantics (*SEM @ACM 2017), pp.65~77 (2017)
- Mohammad, S. M., "Wassa-2017 shared task on emotion intensity", Proceedings of the 8th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis (WASSA-2017) (2017)
- Mohammad, S. M., "Understanding emotions: A dataset of Tweets to study interactions between affect categories" (2018), Proceedings of the 11th Edition of the Language Resources and Evaluation Conference
- Mohammad, S. M., "#Emotional tweets, Proceedings of the First Joint Conference on Lexical and Computational Semantics", Volume 1:Proceedings of the main conference and the shared task, and Volume 2:Proceedings of the Sixth International Workshop on Semantic Evaluation, pp.246~255 (2012)
- Mohammad, S. M., "Emotion intensities in tweets", ~ (2017)
- Mohammad, S. M., "Using hashtags to capture fine emotion categories from tweets", Computational Intelligence, 31(2), pp.301~326 (2014)
- Mohammad, S. M., "Semeval-2018 task 1: Affect in tweets", Proceedings of International Workshop on Semantic Evaluation (SemEval-2018), pp.1~17 (2018)
- Mohammad, S. M., "Semantic role labeling of emotions in tweets", Proceedings of the ACL 2014 Workshop on Computational Approaches to Subjectivity, Sentiment, and Social Media (WASSA), pp.32~41 (2014)
- Mohammad, S. M., "Crowdsourcing a word-emotion association lexicon", Computational Intelligence, 29(3), pp.436~465 (2013)
- Munezero, M., "Emotwitter: A fine-grained visualization system for identifying enduring sentiments in tweets", Computational Linguistics and Intelligent Text Processing (CICLing 2015. Lecture Notes in Computer Science, 9042), 78~91 (2015)
- Nakov, P., "SemEval-2013 task 2: Sentiment analysis in Twitter", Proceedings of the 7th International Workshop on Semantic Evaluation (SemEval 2013), pp.312~320 (2013)
- "Sentimentator: Gamifying fine-grained sentiment annotation" (2018)[URL]
- Pennebaker, J. W., "Psychological aspects of natural language use: our words, our selves", Annual Review of Psychology, 54, pp.547~577 (2003)
- Plutchik, R., "The nature of emotions", American Scientist, 89(4), pp.344~350 (2001)
- Plutchik, R., "Emotion: Theory, reserch, and experience" (1980), Academic press
- Plutchik, R., "Circumplex models of personality and emotions", American Psychological Association, 89, pp.344~350 (1997)
- Rosenthal, S., "Semeval-2014 task 9: Sentiment analysis in Twitter", Proceedings of the 8th International Workshop on Semantic Evaluation (SemEval 2014), pp.73~80 (2014)
- Russell, J. A., "Everyday conceptions of emotion: An introduction to the psychology, anthropology and linguistics of emotion" (1995), Kluwer Academic Publishers
- Sohn, S., "A hybrid approach to sentiment sentence classification in suicide notes", Biomedical Informatics Insights, 5(Suppl. 1), pp.43~50 (2012)
- Sprugnoli, R., "Towards sentiment analysis for historical texts", Digital Scholarship in the Humanities, 31(4), pp.762~772 (2016)
- Strapparava, C., "Semeval-2007 task 14: Affective text", Proceedings of the 4th International Workshop on Semantic Evaluations, pp.70~74 (2007)
- Täckströ M, O., "Semi-supervised latent variable models for sentence-level sentiment analysis", Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies: short papers, 2, pp.569~574 (2011)
- Tian, Y. L., "Recognizing action units for facial expression analysis", Pattern Analysis and Machine the Writerntelligence, the Writ\-erEEE Transactions on, 23(2), pp.97~115 (2001)
- M. J. Vioules, "Detection of suicide-related posts in Twitter data streams", IBM Journal of Research and Development, 62(1), pp.7:1~7:12 (2018), IBM[DOI]
- Wilson, T., "Recognizing contextual polarity: An exploration of features for phrase-level sentiment analysis", Computational Linguistics, 35(3), pp.399~433 (2009)
- Yan, J. L. S., "Exploring fine-grained emotion detection in Tweets", Proceedings of NAACL-HLT 2016, pp.73~80 (2016)
- Yang, M., "A topic model for building fine-grained domain-specific emotion lexicon", Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics, pp.421~426 (2014)
- Zhang, P., "The affective response model: A theoretical framework of affective concepts and their relationships in the ICT context", Management Information Systems Quarterly, 37(1), pp.247~274 (2013)
