디지털콘텐츠학회 논문지 (Journal of Digital Contents Society)

  • 제15권4호
  • /
  • Pages.559-568
  • /
  • 2014
  • /
  • 1598-2009(pISSN)
  • /
  • 2287-738X(eISSN)
한국디지털콘텐츠학회 (Digital Contents Society)
권호 표지
DOI QR코드

DOI QR Code

오피니언 마이닝을 활용한 블로그의 극성 분류 기법

The Blog Polarity Classification Technique using Opinion Mining

  • 이종혁 (숭실대학교 SW특성화대학원) ;
  • 김원상 (숭실대학교 SW특성화대학원) ;
  • 박제원 (숭실대학교 SW특성화대학원) ;
  • 최재현 (숭실대학교 SW특성화대학원)
  • 투고 : 2014.07.11
  • 심사 : 2014.08.31
  • 발행 : 2014.08.31
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

기존의 감정분석을 통한 극성 분류는 주로 평점을 기반으로 하는 상품평을 기준으로 문장규칙을 이용하여 분석해왔다. 이러한 분석방법은 평점이 없는 블로그 같은 경우 적용되기 어려움 점이 있고 댓글 아르바이트나 관리자에 의해 상품평이 조작될 가능성이 있어서 상품평 만으로는 상품, 매장에 대한 의견을 파악하기에는 어려움이 있다. 이러한 문제점을 고려할 때 개인들의 솔직한 의견이 담겨 있는 블로그를 분석하여 극성을 분류하면 상품, 매장에 대한 올바른 이해가 가능하다. 본 논문은 도메인별로 블로그 글에 대한 고빈도 단어를 추출하여 주제어를 선정하고, 선정된 주제어를 기준으로 제안하는 감정분석 기법을 적용하여 블로그 글에 대한 극성을 분류한다. 감정분석 기법의 성능을 평가하기 위하여 정보 검색 분야에서 사용되는 측정지표 Precision, Recall, F-score를 사용하여 본 연구의 극성 분류기법의 유용성을 검증한다. 평가 결과 기존의 상품평을 문장규칙을 이용하여 분석하여 극성 분류를 하는 기법들에 비해서 제안한 감정분석 기법을 적용할 경우에 우수한 성능으로 극성 분류를 하는 것으로 나타났다.

Previous polarity classification using sentiment analysis utilizes a sentence rule by product reviews based rating points. It is difficult to be applied to blogs which have not rating of product reviews and is possible to fabricate product reviews by comment part-timers and managers who use web site so it is not easy to understand a product and store reviews which are reliability. Considering to these problems, if we analyze blogs which have personal and frank opinions and classify polarity, it is possible to understand rightly opinions for the product, store. This paper suggests that we extract high frequency vocabularies in blogs by several domains and choose topic words. Then we apply a technique of sentiment analysis and classify polarity about contents of blogs. To evaluate performances of sentiment analysis, we utilize the measurement index that use Precision, Recall, F-Score in an information retrieval field. In a result of evaluation, using suggested sentiment analysis is the better performances to classify polarity than previous techniques of using the sentence rule based product reviews.

키워드

참고문헌

  1. Jong-Seok Song, Soo-Won Lee, "Automatic Construction of Positive/Negative Feature-Predicate Dictionary for Polarity Classification of Product Reviews", The Korean Institute of Information Scientists and Engineers: Software and Application, Vol. 38, No.3, March 2011.
  2. Xiaowen Ding, Bing Liu, Phips S. Yu, "A Holistic Lexicon-Based Approach to Opinion Mining", Conference on Web Search and Data Mining, 2008
  3. Sung-Ho Oh, Shin-Jae Kang, "Movie Retrieval System by Analyzing Sentimental Keyword from User's Movie Reviews", Journal of Korea Academia-Industrial cooperation Society, Vol. 14, No. 3 pp. 1422-142, July 2013. https://doi.org/10.5762/KAIS.2013.14.3.1422
  4. http://korean.abcthesaurus.com/
  5. Cheol-Seong Lee, Dong-Hee Choi, Seong-Soon Kim Jaewoo Kang, "Classification and Analysis of Emotion in Korean Microblog Texts", The Korean Institute of Information Scientists and Engineers: Database, Vol. 40, No.3, June 2013.
  6. In-Jo Park, "The analysis of Korean affective terms: listing affective terms and exploring dimensions in the affective terms", Seoul National University, Psychology College, Master's thesis, 2001
  7. In-Jo Park, Kyung-Hwan Min, "Making a List of Korean Emotion Terms and Exploring Dimensions Underlying Them", Korean Journal of Social and Personality Psychology, Vol. 19, No. 1, pp. 109-129, 2005.
  8. Hong-June Yune, Han-Joon Kim, Jae-Young Chang "An Efficient Search Method of Product Reviews using Opinion Mining Techniques", The Korean Institute of Information Scientists and Engineers: CPL and Letter", Vol. 16, No. 2, February 2010.
  9. Pavel Smrz., "Using WordNet for Opinion Mining," Proc. of the International WordNet Conference 2006, pp.333-335, 2006.
  10. Andrea Esuli, Fabrizio Sebastiani, "PageRanking WordNet Synsets: An Application to Opinion Mining," Proc. of the Annual Meeting of the Association for Computational Linguistics 2007,pp.424-431, 2007.
  11. Hong-Gu Choi, Een-Jun Hwang, "Emotion-based Music Recommendation System based on Twitter Document Analysis", The Korean Institute of Information Scientists and Engineers: CPL and Letter",Vol. 18, No. 11, November 2012.
  12. Minqing Hu and Bing Liu, "Mining and Summarizing Customer Reviews." KDD'05, Seattle, Washington, USA., Aug.2004.
  13. J. Kamps M. Marx, R. Mokken, and M. de Rijke., "Using WordNet to Measure Semantic Orientations of Adjectives" Proceedings of LREC, 2004.
  14. Hatzivassiloglou V., Mackeown K., "Predicting the Semantic Orientation of Adjectives." Proceedings of the 8th Conference on European chapter of the assocation for Computational Linguistics, pp.174-181,1997
  15. Kwang-Seob Shim, Jae-Hyung Yang, "MACH : A Supersonic Korean Morphological Analyzer", Proceedings of the 19th International Conference on Comp utational Linguistics (COLING-2002), pp.939-945, 2002
  16. Kwang-Mo Ahn, Yun-Suk Kim, and Young-Hoon Kim, Young-Hoon Seo, "Sentiment Classification of Movie Reviews using Levenshtein Distance", Journal of Digital Contents Society Vol. 14, No. 4., pp.581-587, Dec. 2013 https://doi.org/10.9728/dcs.2013.14.4.581

피인용 문헌

  1. A Design of Satisfaction Analysis System For Content Using Opinion Mining of Online Review Data vol.17, pp.3, 2016, https://doi.org/10.7472/jksii.2016.17.3.107
  2. 주가지수 방향성 예측을 위한 도메인 맞춤형 감성사전 구축방안 vol.18, pp.3, 2014, https://doi.org/10.9728/dcs.2017.18.3.585
  3. Analysis of Policy Changes and User Satisfaction of Road Transportation Services using Opinion Mining Techniques vol.21, pp.5, 2014, https://doi.org/10.7855/ijhe.2019.21.5.065
  4. Low-resource YouTube comment encoding for Luganda sentiment classification performance vol.21, pp.5, 2014, https://doi.org/10.9728/dcs.2020.21.5.951
  5. Discovery of knowledge of associative relations using opinion mining based on a health platform vol.24, pp.5, 2020, https://doi.org/10.1007/s00779-019-01231-2