Journal of Internet Computing and Services (인터넷정보학회논문지)

Korean Society for Internet Information (한국인터넷정보학회)
권호 표지
DOI QR코드

DOI QR Code

Trend Analysis using Spatial-Temporal Visualization of Event Information based on Social Media

소셜 미디어에 기반한 이벤트 정보의 시공간적 시각화를 통한 추이 분석

  • Oh, Hyo-Jung (Electronics and Telecommunications Research Institute (ETRI)) ;
  • Yun, Bo-Hyun (Dept. of Computer Education, Mokwon University) ;
  • Yoo, Cheol-Jung (Dept. of Software Engineering, Chonbuk National University) ;
  • Kim, Yong (Dept. of Library & Information Science, Chonbuk National University)
  • Received : 2014.07.21
  • Accepted : 2014.09.22
  • Published : 2014.12.31
Download PDF
⟨ Previous Next ⟩

Abstract

The main focus of this paper is to analyze trend of event informations in a variety of mass media by graphical visualization in axis of the time and location. Especially, continuity analysis based on user-generated social media can reflect the social impact of a certain event according to change time and location and their directional changes. To reveal the characteristics of continuous events, we survey the data set collected from news articles and tweets during two years. Based on case studies on 'disease' and 'leisure', we verify the effectiveness and usefulness of our proposed method. Even though some events occurred during same period, we showed directional changes which have high-impact in social media referred user interest's, compared with fact-based continuous visualization results.

본 논문의 주안점은 다양한 매스 미디어에 나타난 이벤트(event) 정보를 자동으로 인식하고, 이를 시간 및 장소 축으로 시각화함으로써 특정 이벤트의 시간의 흐름에 따른 장소 이동의 추이를 분석하는 데에 있다. 특히 사용자가 직접 작성한 소셜 미디어에 기반하여 이벤트를 추출하고 그들 간의 연속성 분석을 통해 해당 이벤트의 변화 방향성과 사회적 영향을 가늠할 수 있다. 연속성 이벤트의 특성을 규명하기 위해 2년간의 뉴스 기사 및 트윗(tweet)을 수집하여 관련 도메인 선정을 위한 전수조사를 수행하였다. 수행 결과, '질병'과 '여가'도메인을 선정, 본 논문에서 제안한 시각화 방법을 적용한 사례 연구를 통해 시간 및 장소 관점에서의 시각화를 통한 추이 분석의 효용성과 제안된 방법의 유용성을 검증하였다. 특히 단순 사실기반의 연속성 시각과 결과와 사용자의 관심도가 반영된 소셜 미디어에 기반한 연속성 시각화 결과를 비교한 결과, 같은 시기의 이벤트들이라 하더라도 사회적으로 미치는 파장이 큰 장소 이동의 흐름을 파악할 수 있음을 보였다.

Keywords

References

  1. J-H. Do, J-Y. Sim, and J-S, Lee, " Analysis of Spread use of social media and media usage behavior change", Technical Report of Korea Press Foundation, 2010 http://download.kpf.or.kr/MediaPds/PJSFJXLZSKLOX OA.pdf
  2. Jinah Seol, "An Exploratory Study on Social Media Users" Ambivalent Attitude", Journal of Internet Computing and Services(JICS), 15(2), 87-94, 2014 https://doi.org/10.7472/jksii.2014.15.2.87
  3. S-Y. Han, M-H. Choi, M-K, Park, and H-J. Lee, "The Effect of SNS Use on the Social Network: Moderating Effect of the Gender", Journal of Korean Society for Information Management, 30(3). 133-156, 2013. https://doi.org/10.3743/KOSIM.2013.30.3.133
  4. Y. Ho, and S. W. Lee, "Competition and Subsituation of Media: Niche Analysis of Mass Media and Social Media", Korean Journal of Journalism & Communication Studies. 56(4), 29-54, 2012.
  5. S. J Kim, "An Exploratory Study of Undergraduate Students' Health Information Needs and Seeking Behaviors in Social Media", Journal of Korean Biblia Society for Library and Information Science, 23(4), 239-260, 2012. https://doi.org/10.14699/kbiblia.2012.23.4.239
  6. J. Allan, "Topic detection and tracking: event-based information organization", Kluwer Academic Publishers Norwell (ISBN:0-7923-7664-1), 2002.
  7. R. Swan and J. Allan, "Automatic generation of overview timelines", Proceedings of the 23rd annual international ACM SIGIR conference on Research and development in information retrieval. 49-56, 2000.
  8. J. Allan, C. Wade, and A. Bolivar, "Retrieval and novelty detection at the sentence level", Proceedings of the 26th annual international ACM SIGIR conference on Research and development in information retrieval, 314-321, 2003.
  9. Q. He, K. Chang, and E-P, Lim, "Analyzing feature trajectories for event detection", Proceedings of the 30th annual international ACM SIGIR conference on Research and development in information retrieval. 207-214, 2007.
  10. P. Haghani, S. Michel and K. Aberer, "Tracking hot-k items over Web 2.0 streams", Proceedings of the 14. Database Systems for Business, Technology, and Web (BTW 2011), 105-122, 2011.
  11. H. Ma, "Hot topic extraction using Time Window", Proceedings of International Conference on Machine Learning and Cybernetics (ICMS-2011). 56-60, 2007.
  12. A. Mislove, S. Lehmann, et al., "Pulse of the nation: Us mood throughout the day inferred from twitter", Accessed November 22, 2010. http://www.ccs.neu.edu/home/amislove/twittermood/
  13. T. Sakaki, M. Okazaki, and Y. Matsuo, "Earthquake shakes twitter users: real-time event detection by social sensors", Proceedings of the 19th international conference on World wide web (WWW '10). 851-860, 2010.
  14. M. Imran, S. Elbassuoni, et al., "Practical extraction of disaster-relevant information from social media", Proceedings of the 22nd international conference on World wide web (WWW '13). 1021-1024, 2013.
  15. (C)United State Tornades http://www.ustornadoes.com/
  16. H-J. Oh, Y-J. Bae, and B-H. Yun, "Temporal and Spatial Continuity Analysis of Issue Events", Journal of KIIT. 11(9), 161-167, 2013
  17. H-J. Oh, H-K. Kim, and B-H. Yun, "Continuous Issue Event Analysis in Social Media", The Journal of Korean association of computer education, 17(2), 31-38, 2014.
  18. B-H. Yun, "Comparison of Sentence-level Event Classification Algorithms", Journal of KIIT. 10(6), 171-176, 2012.
  19. S. Liy, S. & H. Chang, "A Topic Detection and Tracking System with TF-Density", Lecture Notes in Electrical Engineering, 156. 115-1203, 2013. https://doi.org/10.1007/978-3-642-28807-4_17