DOI QR코드

DOI QR Code

Political Information Filtering on Online News Comment

정보 중립성 확보를 위한 인터넷 뉴스 댓글의 정치성향 분석

  • 최혜봉 (한동대학교 ICT 창업학부) ;
  • 김재홍 (한동대학교 커뮤니케이션학부) ;
  • 이지현 (한동대학교 전산전자공학부) ;
  • 이민구 (한동대학교 커뮤니케이션학부)
  • Received : 2020.10.30
  • Accepted : 2020.11.20
  • Published : 2020.11.30

Abstract

We proposes a method to estimate political preference of users who write comments on internet news. We collected and analyzed a massive amount of new comment data from internet news to extract features that effectively characterizes political preference of users. We expect that it helps user to obtain unbiased information from internet news and online discussion by providing estimated political stance of news comment writer. Through comprehensive tests we prove the effectiveness of two proposed methods, lexicon-based algorithm and similarity-based algorithm.

본 연구는 인터넷 뉴스 댓글 빅데이터 분석을 통해 뉴스 댓글 사용자의 정치적 성향을 추정하는 방법을 제안한다. 인터넷 뉴스 댓글과 작성자의 정치 성향을 함께 제공하여 디지털 매체를 통한 정보 전달의 객관성과 중립성을 확보하고자 한다. 250만 건 이상의 인터넷 뉴스 댓글의 특성을 분석하고 사용자의 정치적 성향을 효과적으로 추정하기 위한 특징을 추출한다. 어휘사전 기반 알고리즘과 유사도 기반 알고리즘을 제안하고 실험을 통해 두 알고리즘을 비교하고 효과를 검증한다.

Keywords

References

  1. Korea Press Foundation, "Media Users in Korea 2019", 2019.
  2. Y.H.. Kang. J.H. Kim., "A research of user perspective value and awareness of online comments", The Korean Psychological Association, p . 92-92, 2018.
  3. Y.J. Jang, E.J. Lee, "The Effect of Reading, Writing, and Diversity in Online Bulletin Discussions", Korean Society For Journalism And Communication Studies, p . 95-97, 2009.
  4. I.K. Jung, Y.S. Kim,, "A Study on the Influence of Online Media on Public Opinion", Korean Society For Journalism And Communication Studies, pp. 653-672, 2006.
  5. Y.S. Kim, S.M. Hong, "0.1% of the comments are 30%... Sixty-five percent of malicious comments are swear words-threats", DongAIlbo, /https://www.donga.com/news/Society/article/all/20090115/8684451/9 (retrieved Jan, 17, 2009).
  6. K.D. Hyun, N.K. Jung, M.H. Seo, "Examining the Effects of Perceived Partisan Slants of News and User Comments from Portal News Sites on Portal News Trust, Third Person Perception and Selective Exposure : Comparisons of Conservative and Progressive Users", Korean Society For Journalism And Communication Studies, Vol. 64, No. 4, p . 247-288, 2020. DOI:10.20879/kjjcs.2020.64.4.007
  7. S.W. Kim, H.W. Ahn, Y.N. Jang, M.Y. Hong, M.J. Seo, S.T. Kim, "A Big-data Study of YouTube Comments to Classify Customer Journey Decisions- Proposing a New Exploratory Analysis Method-", Research Institue for Image & Cultural Contents, Vol. 16, p . 57-89, 2019. DOI:10.24174/jicc.2019.02.16.57
  8. C.W. Kim, B.K. Jung, "The Political Recognition Surrounding Candlelight Rally and Taegeukgi Rally: A Big Data Analytics on Online News Comments", The Convergent Research Society Among Humanities, Sociology, Science, and Technology, Vol. 8, No. 6, p . 875-885, 2018.
  9. S.H. Moon, "A Study on Securing Global Big Data Competitiveness based on its Environment Analysis", The Journal of the Convergence on Culture Technology, Vol. 5, No. 2, pp. 361-366, 2019. DOI:https://doi.org/10.17703/JCCT.2019.5.2.361
  10. J.K. Roh, Y. Min, "Efects of Politically Motivated Selective Exposure on Attitude Polarization : A Study of Non-Political Online Community Users", Korean Society For Journalism And Communication Studies, Vol. 56, Vol. 2, p . 226-248, 2012.
  11. E.J. Lee, "Social Identity Model of Deindividuation Effects: Theoretical Implications and Future Directions, Korean Society For Journalism And Communication Studies", Vol. 4, No. 1, p . 7-31, 2008.
  12. E.J. Lee, "Deindividuation effects on group polarization in computer-mediated communication: The role of group identification, public-self-awareness, and perceived argument quality", Journal of communication, Vol. 57, No. 2, pp. 385-403. 2007. DOI:10.1111/j.1460-2466.2007.00348.x
  13. Y.G. Lee, J.Y. Han, M.Y. Cha, "Building a Political Bias Classifier for News Comments using User Labeling", The Korean Institute of Information Scientists and Engineers, p . 1643-1645, 2020.
  14. M.S. Ann, "A Public Perception Study on the new word "Corona Blue":Focusing on Social Media Big Data Analysis", International Journal of Advanced Culture Technology, Vol. 8, No. 3, pp. 133-139, 2020. DOI:https://doi.org/10.17703/IJACT.2020.8.3.133
  15. H.J. Won, H.Y. Lee, S.S. Kang, "A Performance Comparison of Korean Morphological Analyzers for Large-scale Text Analysis", The Korean Institute of Information Scientists and Engineers, p . 401-403, 2020.
  16. H.W. Jeon, "KoNLP: Korean NLP Package. R Package Version 0.80.2", https://github.com/haven-jeon/KoNLP, 2016.
  17. H.W. Jeon, "Kospacing: Automatic korean word spacing", https://github.com/haven-jeon/KoSpacing, 2018.
  18. H.C. Chae, J.G. Lee, Y.N. Choi, D.H. Park, Y.W. Chung, Sentiment "Analysis of Foot-and-Mouth Disease Using Tweet Text-Mining Technique", Korea Information Processing Society, Vol. 7, No. 11, p . 419-426, 2018.
  19. K.G. Lyu, "A Method for Constructing Sentiment Dictionary using Social Media and Collective Intelligence", The Korean Institute of Information Scientists and Engineers, p . 664-666, 2018.
  20. J.K. An, H.W. Kim, "Building a Korean Sentiment Lexicon Using Collective Intelligence", Korea Intelligent Information Systems Society, Vol. 21, No. 2, p . 49-67, 2015. https://doi.org/10.13088/jiis.2015.21.2.49
  21. H.S. Jang, K.Y. Jeong, E.Y. Jang, "Eficient method to generate sentiment vocabulary for specific topic based on Word2Vec", The Korean Institute of Information Scientists and Engineers, p . 652-654, 2017.
  22. H.B. Choi, "Sentiment Analysis of E-commerce Review Data and Adaptable Sentiment Lexicon", The Korean Society of Culture and Convergence, Vol. 42, No.1, pp. 357-378, 2020. https://doi.org/10.33645/cnc.2020.01.42.1.357
  23. B.W. On, S.M. Park, C.W. Na, "KNU Korean Sentiment Lexicon Kunsan National University Dept. of Software Convergence Engineering Data Intelligence Lab", https://github.com/park1200656/KnuSentiLex, 2018.
  24. J.H. Lee, S.H. Jung, J.H. Kim, E.J. Min, U.Y. Yeo, J.W. Kim, "Product Evaluation Criteria Extraction through Online Review Analysis : Using LDA and k-Nearest Neighbor Approach", Korea Intelligent Information Systems Society, Vol. 26, No. 1, p . 97-117, 2020