한국어 구문분석을 활용한 이유-감성 패턴 기반의 감성사전 구축
Sentiment Dictionary Construction Based on Reason-Sentiment Pattern Using Korean Syntax Analysis
2
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
Sentiment analysis is a method used to comprehend feelings, opinions, and attitudes in text, and it is essential for evaluating consumer feedback and social media posts. However, creating sentiment dictionaries, which are necessary for this analysis, is complex and time-consuming because people express their emotions differently depending on the context and domain. In this study, we propose a new method for simplifying this procedure. We utilize syntax analysis of the Korean language to identify and extract sentiment words based on the Reason-Sentiment Pattern, which distinguishes between words expressing feelings and words explaining why those feelings are expressed, making it applicable in various contexts and domains. We also define sentiment words as those with clear polarity, even when used independently and exclude words whose polarity varies with context and domain. This approach enables the extraction of explicit sentiment expressions, enhancing the accuracy of sentiment analysis at the attribute level. Our methodology, validated using Korean cosmetics review datasets from Korean online shopping malls, demonstrates how a sentiment dictionary focused solely on clear polarity words can provide valuable insights for product planners. Understanding the polarity and reasons behind specific attributes enables improvement of product weaknesses and emphasis on strengths. This approach not only reduces dependency on extensive sentiment dictionaries but also offers high accuracy and applic- ability across various domains.
Abstract
Sentiment analysis is a method used to comprehend feelings, opinions, and attitudes in text, and it is essential for evaluating consumer feedback and social media posts. However, creating sentiment dictionaries, which are necessary for this analysis, is complex and time-consuming because people express their emotions differently depending on the context and domain. In this study, we propose a new method for simplifying this procedure. We utilize syntax analysis of the Korean language to identify and extract sentiment words based on the Reason-Sentiment Pattern, which distinguishes between words expressing feelings and words explaining why those feelings are expressed, making it applicable in various contexts and domains. We also define sentiment words as those with clear polarity, even when used independently and exclude words whose polarity varies with context and domain. This approach enables the extraction of explicit sentiment expressions, enhancing the accuracy of sentiment analysis at the attribute level. Our methodology, validated using Korean cosmetics review datasets from Korean online shopping malls, demonstrates how a sentiment dictionary focused solely on clear polarity words can provide valuable insights for product planners. Understanding the polarity and reasons behind specific attributes enables improvement of product weaknesses and emphasis on strengths. This approach not only reduces dependency on extensive sentiment dictionaries but also offers high accuracy and applic- ability across various domains.
참고문헌 (48)
- Aggarwal, C. C., "Machine learning 150 Woo Hyun Kim․Heejung Lee for text: An introduction" (2018), Springer International Publishing
- 안정국, "집단지성을 이용한 한글 감성어 사전 구축", 지능정보연구, 21(2), pp.49~67 (2015), 한국지능정보시스템학회
- Ahmed, M., "Constructing do-main-dependent sentiment dictionary for sentiment analy-sis", Neural Computing and Applications, 32, pp.14719~14732 (2020)
- Alshari, E. M., "Effective method for sentiment lexical dictionary enrichment based on Word2Vec for sentiment analysis", fourth international conference on information retrieval and knowledge management, IEEE (2018)
- Baccianella, S., "Sentiwordnet 3.0: An enhanced lexical resource for sentiment analysis and opinion mining", Lrec (2010)
- Behdenna, S., "Sentiment analysis at document level", Smart Trends in Information Technology and Computer Communications:First International Conference (2016)
- Bian, S., "A new Chinese financial sentiment dictionary for textual analysis in ac-counting and finance", ~ (2021)
- Birjali, M., "A compre-hensive survey on sentiment analysis: Approaches, chal-lenges and trends", Knowledge-Based Systems, 226, pp.107134~ (2021)
- Cambria, E., "Senticnet: A publicly available semantic resource for opinion mining", 2010 AAAI fall symposium series (2010)
- Cambria, E., "Senticnet 2:A semantic and affective resource for opinion mining and sentiment analysis", Twenty-Fifth interna-tional FLAIRS conference (2012)
- Cho, S. H., "Text sentiment classification for SNS-based marketing using domain sentiment dic-tionary", IEEE International Conference on Consumer Electronics (2012)
- Do, H. H., "Deep learning for aspect-based sentiment analysis : a com-parative review", Expert Systems with Applications, 118, pp.272~299 (2019)
- Havasi, C., "ConceptNet: A lexical resource for common sense knowledge", Recent advances in natural language processing V: selected papers from RANLP, 309, pp.269~ (2007)
- 허찬, "Word2vec와 Label Propagation을 이용한 감성사전 구축 방법", 한국차세대컴퓨팅학회 논문지, 13(2), pp.93~101 (2017), 한국차세대컴퓨팅학회
- Hong, Y., "A Korean Syntactic Analyzer based on the Dependency Grammar", KIISE Conference, pp.781~784 (1993)
- Hutto, C., "Vader : A parsimonious rule-based model for sentiment analysis of social media text", Proceedings of the International AAAI Conference On Web and Social Media (2014)
- Jiaheng, H., "Constructing sentiment dictionary with deep learning : Case study of financial data", Data Analysis and Knowledge Discovery, 2(10), pp.95~102 (2018)
- Jurafsky, D., "Speech and language proc-essing" (2019), Pearson Education India
- Kim, J., "Remarks on"Sentence"", Poetics and Linguistics, 6, pp.65~113 (2003)
- 김정호, "그래프 기반 준지도 학습 방법을 이용한 특정분야 감성사전 구축", 감성과학, 18(1), pp.103~110 (2015), 한국감성과학회[DOI]
- Kudo, T., "Applying conditional random fields to Japanese morphological analysis", Proceedings of the conference on empirical methods in natural language processing (2004)
- Kwon, O., "KHU-SentiwordNet: Developing A Korean SentiwordNet Combining Empty Morpheme", Korea Society of IT Service Conference, pp.194~197 (2019)
- 이종화, "SNS대상의 지능형 자연어 수집, 처리 시스템 구현을 통한 한국형 감성사전 구축에 관한 연구", 정보시스템연구, 29(3), pp.237~251 (2020), 한국정보시스템학회
- Li, S., "A deep learn-ing-based approach to constructing a domain sentiment lexicon : A case study in financial distress prediction", Information Processing and Management, 58(5), pp.102673~ (2021)
- Lim, J., "Korean Sentiment Dictionary Construction Based on Reason-Sentiment Pattern Using Korean Syntax Analysis 151Dependency Guidelines for Dependency Parsking and Exo-Brain Language Analysis Corpus", Hangul and Korean Information Processing Conference (2015)
- Liu, H., "ConceptNet—a practical common-sense reasoning tool-kit", BT Technology Journal, 22(4), pp.211~226 (2004)
- Liu, B., "Handbook of natural language processing" (2010)
- Liu, B., "Sentiment analysis and opinion mining" (2022), Springer Nature
- Mel'cuk, I. A., "Dependency syntax : theory and practice" (1988), SUNY press
- Nazir, A., "Issues and challenges of aspect-based sentiment analysis : A compre-hensive survey", IEEE Transactions on Affective Computing, 13(2), pp.845~863 (2020)
- Nivre, J., "Dependency grammar and dependency parsing", MSI report, 5133(1959), pp.1~32 (2005)
- Manning, C. D., "Universal dependencies v1: A multilingual treebank collection", Proceedings of the Tenth International Conference on Language Resources and Evaluation (2016)
- Park, K., "An empirical study of tokenization strategies for various Korean NLP tasks", arXiv preprint arXiv : 2010. 02534, ~ (2020)
- Park, S., "Klue : Korean language understanding evaluation", arXiv preprint arXiv : 2105. 09680, ~ (2021)
- 박상민, "Bi-LSTM 기반의 한국어 감성사전 구축 방안", 지능정보연구, 24(4), pp.219~240 (2018), 한국지능정보시스템학회
- Plutchik, R., "Theories of emotion" (1980), Academic press
- Poria, S., "Enhanced SenticNet with affective labels for concept-based opinion mining", IEEE Intelligent Systems, 28(2), pp.31~38 (2013)
- 신동혁, "한국어 감성 사전 DecoSelex 구축을 위한 영어 SentiWordNet 활용 및 보완 논의", 한국사전학, (28), pp.75~111 (2016), 한국사전학회[DOI]
- Sivasankar, E., "An enhanced sentiment dictionary for domain adapta-tion with multi-domain dataset in Tamil language(ESD-DA)", Soft Computing, 25, pp.3697~3711 (2021)
- 송종석, "상품평 극성 분류를 위한 특징별 서술어 긍정", 부정 사전 자동 구축, 2011, pp.38(3), 157~168[DOI]
- Song, K., "Build emotion lexicon from microblogs by combining effects of seed words and emoticons in a heterogeneous graph", Proceedings of the 26th ACM Conference on Hypertext and Social Media (2015)
- Steinberger, J., "Creating sentiment dic-tionaries via triangulation", Decision Support Systems, 53(4), pp.689~694 (2012)
- Tan, A. H., "Text mining: The state of the art and the challenges", Proceedings of the Pakdd Workshop on Knowledge Disocovery from Advanced Databases (1999)
- Tesniere, L., "Elements de syntaxe structural", Editions Klincksieck, ~ (1959)
- Tsai, A. C. R., "Building a concept-level sentiment dictionary based on commonsense knowledge", IEEE Intelligent Systems, 28(2), pp.22~30 (2013)
- Yang, L., "Sentiment analysis for E-commerce product reviews in Chinese based on sentiment lexicon and deep learning", IEEE access, 8, pp.23522~23530 (2020)
- Yang, Y, "Aspect-Level Opinion Pattern Mining Using Dependency Relations in Product Reviews", Master’s, pp.2023
- Yue, L., "A survey of sentiment analysis in social media", Knowledge and Information Systems, 60, pp.617~663 (2019)