본문 바로가기
KERD
논문KCI 등재

DECO 감성사전과 LGG 문법에 기반한 관광 숙박 온라인 후기글의 감성 분석 연구

Sentiment Analysis of Airbnb Reviews based on DECO Dictionary & LGGs

0

조회

0

다운로드

2

인용

0

참고문헌

키워드

주제분류사전학

초록

This study proposes a Sentiment Analysis of Airbnb users' reviews of Jeju Island (Korean tourist attraction) based on DECO Korean dictionary and Local Grammar Graphs(LGGs). As a result of classification utilizing DecoSentiClassifier, 97% reviews turned out to be ‘Positive’. Moreover, we investigated time-series trend graphs, co-occurrence network, and term-frequency tables of the two most popular districts (Seogwipo-si and Jeju-si) of Jeju. Unlike the related studies mostly rooted in machine learning methods such as statistic classification or automatic lexical expansion, this research focuses on lexical algorithmic classification based on DECO dictionary for simple words and LGG formalism for multi-word expressions such as polarity-shifted sequences. Sentiment analysis based on elaborated language resources enhances overall reliability of the analysis and makes accessible a bootstrap approach, clarifying the primary significance of this study.

Abstract

This study proposes a Sentiment Analysis of Airbnb users' reviews of Jeju Island (Korean tourist attraction) based on DECO Korean dictionary and Local Grammar Graphs(LGGs). As a result of classification utilizing DecoSentiClassifier, 97% reviews turned out to be ‘Positive’. Moreover, we investigated time-series trend graphs, co-occurrence network, and term-frequency tables of the two most popular districts (Seogwipo-si and Jeju-si) of Jeju. Unlike the related studies mostly rooted in machine learning methods such as statistic classification or automatic lexical expansion, this research focuses on lexical algorithmic classification based on DECO dictionary for simple words and LGG formalism for multi-word expressions such as polarity-shifted sequences. Sentiment analysis based on elaborated language resources enhances overall reliability of the analysis and makes accessible a bootstrap approach, clarifying the primary significance of this study.

참고문헌 (45)

  1. 김문형, "KOSAC: 한국어 감정 및 의견 분석코퍼스", 한국정보과학회 학술발표논문집, 6, pp.650~652 (2013), 한국정보과학회
  2. 김명규, "텍스트 문서 기반의 감성 인식 시스템", 감성과학, 12(4), pp.433~442 (2009), 한국감성과학회
  3. 남지순, "오피니언 극성을 전환하는 한국어 부정표현 자동 인식을 위한 연구", 언어와언어학, (57), pp.61~94 (2012), 언어연구소
  4. 남지순, "오피니언 극성 전환 장치 ‘너무’와 공기하는 서술어 유형에 대한 연구", 언어과학, 19(4), pp.89~123 (2012), 한국언어과학회
  5. "최근 온라인 구매 행태와 시사점조사" (2009)[URL]
  6. "‘전문가’ 의견과 ‘연예인브랜드’보다 ‘사용자 경험’을 더 중시하는 소비자들" (2017)[URL]
  7. 신동혁, "한국어 감성 사전 DecoSelex 구축을 위한 영어 SentiWordNet 활용 및 보완 논의", 한국사전학, (28), pp.75~111 (2016), 한국사전학회
  8. 송종석, "상품평 극성 분류를 위한 특징별 서술어 긍정", 부정 사전 자동 구축, 2011, pp.38(3), 157~168[DOI]
  9. 송순, "에어비앤비(Airbnb) 사례를 통해 본 공유경제 관련 법 제정 현황분석", 월간 소비자정책동향, 64, pp.19~36 (2015), 한국소비자원
  10. 이상훈, "영역별 맞춤형 감성사전 구축을 통한 영화리뷰 감성분석", 지능정보연구, 22(2), pp.97~113 (2016), 한국지능정보시스템학회
  11. 정의철, "감정용언의 부정 구문에 대한 연구-극성의 정도성과 의미 범주의 변화를 중심으로-", 어문학, (127), pp.25~53 (2015), 한국어문학회
  12. 조동희, "MUSE 감성주석코퍼스 구축을 위한 분류 체계 및 태그셋 연구", 우리말연구, (47), pp.5~47 (2016), 우리말학회
  13. Akkaya, C, "Amazon Mechanical Turk for subjectivity word sense disambiguation", Proceedings of the NAACL HLT 2010 Workshop on Creating, Speech and Language Data with Amazon’s Mechanical Turk, pp.195~203 (2010)
  14. Baccianella, S, "SentiWordNet 3.0: An enhanced lexical resource for sentiment analysis and opinion mining", 7th LREC, pp.2200~2204 (2010)
  15. Choi, Y, "Adapting a polarity lexicon using integer linear programming for domain-specific sentiment classification", Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing, 2, pp.590~598 (2009)
  16. Das, A, "SentiWordNet for Indian Languages", the 8th Workshop on Asian Language Resources(ALR), pp.56~63 (2010)
  17. Das, A, "Towards the global SentiWordNet", PACLIC 24 Proceeding, pp.799~809 (2011)
  18. Dave, K, "Mining the peanut gallery:Opinion extraction and semantic classification of product reveiws", Proceedings of WWW '03 Proceedings of the 12th international conference on World Wide Web, pp.519~528 (2003)
  19. Deng, L, "MPQA 3.0: An Entity", Event-Level sentiment corpus, 2015, 1323~1328
  20. Du, X, "Adapting information Bottleneck method for automatic construction of domain-oriented sentiment lexicon", Proceedings of the 3rd ACM International Conference on Web Search and Data Mining, pp.111~120 (2010)
  21. Esuli, A, "SENTIWORDNET: A publicly available lexical resource for opinion mining", Proceedings of the 5th Conference on Language and Evaluation(LREC 06), pp.417~422 (2006)
  22. Gross, M, "Finite-state language processing", pp.329~354 (1997), The MIT Press
  23. Gross, M, "A Bootstrap method for constructing local grammars", Proceedings of the Symposium on Contemporary Mathematics, University of Belgrad, pp.229~250 (1999)
  24. Hatzivassiloglou, V, "Predicting the semantic orientation of adjectives", Proceedings of the 35th Annual Meeting of the Association for Computational Linguistics and 8th Conference of the European Chapter of the Association for Computational Linguistics, pp.174~181 (1997)
  25. Hu, M, "Mining and summarizing customer reviews", Proceedings of ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDDᐨ2004) (2004)
  26. Kanayama, H, "Fully automatic lexicon expansion for domain-oriented sentiment analysis", Proceedings of the 2006Conference on Empirical Methods in Natural Language Processing, pp.355~363 (2006)
  27. Liu, B, "Sentiment analysis and opinion mining" (2012), Morgan & Claypool Publishers
  28. Liu, B, "Sentiment Analysis: mining opinions, sentiments, and emotions" (2015), Cambridge Univ Press
  29. Nam, J, "A Novel dichotomy of the Korean adverb nemwu in opinion classification", Studies in Language, 38(1), pp.169~207 (2014), John Benjamins Publishing Company
  30. Korean Electronic Dictionary DECO, "Nam, J", Hankuk University of Foreign Studies, ~, pp.TRᐨ2015ᐨ02 (2015)
  31. Statistical results of MUSE, "Nam, J", Hankuk University of Foreign Studies, ~, pp.TRᐨ2016ᐨ08 (2016)
  32. Pang, B, "Thumb up? Sentiment classification using machine learning techniques", Proceedings of the 2002 Conference on Empitical Methods in Natural Language Processing, pp.79~86 (2002)
  33. Paumier, S, "De la reconnaissance de formes linguistiques a l’analyse syntaxique", Ph. D, pp.2003
  34. Paumier, S, "Un système de dictionnaire de mots simples du coréen", Penser le Lexique Grammaire. Editions Honore Champion, 481~490 (2014)
  35. Piryani, R, "Analytical mapping of opinion mining and sentiment analysis research during 2000∼2015", Information Processing and Management, 53, pp.122~150 (2017)
  36. Sul, K, "Trading on Twitter: The financial information content of emotion in social media", System Sciences (HICSS), 2014 47th Hawaii International Conference on, pp.806~815 (2014)
  37. Taboada, M, "Lexicon-Based Methods for Sentiment Analysis", Computational Linguistics, 37(2), pp.267~307 (2011)
  38. Turney, P. D, "Thumbs up or thumbs down? Semantic orientation applied to unsupervised classification of reviews", Proceedings of the 40th annual meeting of the Association for Computational Linguistics, pp.417~424 (2002)
  39. Thelwall M, "Sentiment strength detection for the social Web", Journal of the American Society for Information Science and Technology, 63(1), pp.163~173 (2012)
  40. Vu, X-S, "Construction of Vietnamese SentiWordNet using Vietnamese dictionary and string kernel Function", Master, pp.2014
  41. Wiebe J, "Annotating expressions of opinions and emotions in language", Language Resources and Evaluation, 39(2ᐨ3), pp.165~210 (2005)
  42. Wilson, T, "Fine-grained subjectivity analysis", PhD, pp.2008
  43. Xu, C, "Evaluating the ‘geographical awareness’ of individuals: an exploratory analysis of twitter data", Cartography and Geographic Information Science, 40(2), pp.103~115 (2013)
  44. DecoTex users’ manual, "Yoo, G", Hankuk University of Foreign Studies, ~, pp.TR-2017-12 (2017)
  45. The rise of the sharing economy: Estimating the impact of Airbnb on the hotel industry, "Zervas, G", Boston U. School, 1~45, pp.Paper No. 2013ᐨ16 (2015)

관련 논문AI추천

이 간행물의 다른 논문 (6건)