An Experimental Study on Building A Chinese Domain-Dependent Sentiment Lexicon
2
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
This study proposes an experimental approach to build a domain-dependent sentiment lexicon that is crucial for sentiment analysis of Chinese texts in the Deco Sentiment Analysis platform developed in Digital Language and Knowledge Contents Research Association (DICORA research center). More than 150,000 hotel review data were trained with word2vec models, and 80 emotional words were first selected as seed words. TF-IDF notion was used to measure the importance of the sentiment vocabulary in hotel reviews. In order to build the feature vector representation of each candidate word, the similarities between a term and the other 80 seed words were calculated and the upcoming step was expanding the lexicon with a double propagation method that requires recognizing feature words related to the sentiment expressions. Through the bootstrap of sentiment terms and features, the expansion of the sentiment lexicon could be performed. The evaluation of the expanded result is confirmed with rates set at 77.4% of precision and 92.6% of recall performance.
Abstract
This study proposes an experimental approach to build a domain-dependent sentiment lexicon that is crucial for sentiment analysis of Chinese texts in the Deco Sentiment Analysis platform developed in Digital Language and Knowledge Contents Research Association (DICORA research center). More than 150,000 hotel review data were trained with word2vec models, and 80 emotional words were first selected as seed words. TF-IDF notion was used to measure the importance of the sentiment vocabulary in hotel reviews. In order to build the feature vector representation of each candidate word, the similarities between a term and the other 80 seed words were calculated and the upcoming step was expanding the lexicon with a double propagation method that requires recognizing feature words related to the sentiment expressions. Through the bootstrap of sentiment terms and features, the expansion of the sentiment lexicon could be performed. The evaluation of the expanded result is confirmed with rates set at 77.4% of precision and 92.6% of recall performance.
참고문헌 (30)
- 장경철, "The English Transitive Phrasal Verb Revisited", 언어과학, 26(3), pp.101~121 (2019), 한국언어과학회[DOI]
- Che, W. X., "LTP: A Chinese Language Technology Platform", Proceedings of the Coling, pp.13~16 (2010)
- Chen, J., "Document Classification Method Based on Word2vec", Computer Systems & Applications, 26(11), pp.159~164 (2017)
- Gao, B., "Research on the Impact of Online Reviews on Hotel Booking Rate", Tourism Tribune, 2016, pp.31(4), 109~117
- Hassan, A., "Identifying Text Polarity Using Random Walks", pp.395~403 (2010), Association for Computational Linguistics
- "HowNet 2011"[URL]
- Hu, M., "Mining Opinion Features in Customer Reviews", Proc. of the 19th National Conference on Artificial Intelligence, pp.755~760 (2001), AAAI Press
- Users’ Manual of DecoSentA Platform, "Hwang, C. H.", DICORA. Hankuk University of Foreign Studies, ~, pp.DICORA-TR-2019-01 (2019)
- Kim, S. M., "Determining the Sentiment of Opinions", Proceedings of the 20th International Conference on Computational Linguistics, pp.1367~1373 (2004), Association for Computational Linguistics
- 김선영, "복수전공자의 학습사회화과정에 대한 연구:SNS 기반 학습공동체를 중심으로", 언어과학, 27(3), pp.21~47 (2020), 한국언어과학회[DOI]
- 김태희, "한국 대학생들의 영어 작문에서 접속어 사용 코퍼스 분석", 언어과학, 27(3), pp.79~102 (2020), 한국언어과학회[DOI]
- Laurens, V. D. M, "Accelerating t-SNE using Tree-based Algorithms", Journal of Machine Learning Research, 15(1), pp.3221~3245 (2014)
- Li S. Y., "Sentiment Analysis Solution Based on Hotel Product Reviews", Computer Systems & Applications, pp.227~231 (2017)
- Liu B., "Sentiment Analysis: Mining Opinions, Sentiments, and Emotions", pp.367~ (2015), Cambridge Univ Press
- Lin, J. H., "Building of Domain Sentiment Lexicon Based on Word2vec", Journal of Shandong University (Engineering Science), 48(3), pp.40~47 (2018)
- DECO Korean Electronic Dictionary, "Nam, J. S.", DICORA. Hankuk University of Foreign Studies, ~, pp.DICORA-TR-2012-02 (2012)
- Nam, J. S, "An Introduction to a Methodology of Inplementing Korean Electronic Dictionaries for Corpus Analysis", pp.672~ (2018), Youkrack Publishing Company
- Paumier, S., "Users’ Manual of UNITEX, LIGM" (2003), University of Marne-la-Vallee
- Peng, L-Z., "Semantic Similarity Computing based on Community Mining of Wikipedia", Computer Science, 43(4), pp.45~49 (2016)
- Qiu, G., "Opinion Word Expansion and Target Extraction through Double Propagation", Computational Linguistics, 37(1), pp.9~27 (2011)
- Shi, J. L., "Commendatory Words Dictionary" (2005), Sichuan Dictionary Publishing House
- Singh, V. K., "Sentiment Analysis of Movie Reviews: A New Feature-based Heuristic for Aspect-level Sentiment Classification", International Multi-Conference on Automation, Computing, Communication, Control and Compressed Sensing (iMac4s), pp.712~717 (2013), IEEE
- Song, B. T., "An Empirical Study of Sentiment Analysis for Chinese Documents", Expert Systems with Applications, 34(4), pp.2622~2629 (2008)
- Wang, L. Y., "An Approach to Chinese Sentiment Lexicon Construction Based on Conjunction Relation", China Computational Linguistics, (010), pp.1~8 (2015)
- Xu, L. H., "Constructing the Affective Lexicon Ontology", Journal of the China Society for Scientific and Technical Information, 27(2), pp.180~185 (2018)
- Yang, X. P., "Automatic Construction and Optimization of Sentiment Lexicon based on Word2Vec", Computer Science, 2017(44), pp.42~48 (2017)
- Yang, D., "Classification Approach of Chinese Texts Sentiment based on Semantic Lexicon and Naive Bayesian", Application Research of Computers, 27(10), pp.3737~3743 (2010)
- Yuan, H. X, "A Method of Constructing Sentiment Lexicon Based on Word2Vec and HowNet", Modern Computer, 2018(02), pp.9~13 (2018)
- Zhang, W., "A Dictionary of Commendatory and Derogatory Words Dictionary for Students" (2004), China Encyclopedia Press
- Zhou, Y. M., "Construction Method of Sentiment Lexicon for News Reviews", Computer Science, 8, pp.67~70 (2014)