DOI QR코드

DOI QR Code

Study on the Methodology for Extracting Information from SNS Using a Sentiment Analysis

SNS 감성분석을 이용한 정보 추출 방법론에 관한 연구

  • Hong, Doopyo (Korea Expressway Corporation Gwangju Jeonnam Regional Headquarters) ;
  • Jeong, Harim (Dept. of Civil and Transportation Eng., Ajou University) ;
  • Park, Sangmin (Dept. of Civil and Transportation Eng., Ajou University) ;
  • Han, Eum (Traffic Science Institute, Korea Road Traffic Authority) ;
  • Kim, Honghoi (Ilmile Corp.) ;
  • Yun, Ilsoo (Dept. of Transportation System Eng., Ajou University)
  • 홍두표 (한국도로공사 전남지역본부) ;
  • 정하림 (아주대학교 건설교통공학과) ;
  • 박상민 (아주대학교 건설교통공학과) ;
  • 한음 (도로교통공단 교통과학연구원) ;
  • 김홍회 (일마일주식회사) ;
  • 윤일수 (아주대학교 교통시스템공학과)
  • Received : 2017.01.03
  • Accepted : 2017.11.06
  • Published : 2017.12.31

Abstract

As the use of SNS becomes more active, many people are posting their thoughts about specific events in their SNS in the form of text. As a result, SNS is used in various fields such as finance and distribution to conduct service satisfaction surveys and consumer monitoring. However, in the transportation area, there are not enough cases to utilize unstructured data analysis such as emotional analysis. In this study, we developed an emotional analysis methodology that can be used in transportation by using highway VOC data, which is atypical data collected by Korea Expressway Corporation. The developed methodology consists of morpheme analysis, emotional dictionary construction, and emotional discrimination of the collected unstructured data. The developed methodology was verified using highway related tweet data. As a result of the analysis, it can be guessed that many information and information about the construction and the accident were related to the highway during the analysis period. Also, it seems that users complain about the delay caused by construction and accident.

최근 SNS 이용이 활발해짐에 따라 많은 사람들이 특정 이벤트 등에 대한 자신들의 생각을 비정형 데이터인 텍스트 형태로 자신의 SNS에 게시하고 있다. 이에 따라 금융, 유통 등 다양한 분야에서 이미 SNS를 이용하여 서비스 만족도 조사, 소비자 요구사항 모니터링, 대선 후보 선호도 등을 수행하고 있다. 하지만 교통 분야에서는 감성분석과 같은 비정형 데이터 분석을 활용하는 사례가 부족한 실정이다. 이에 본 연구에서는 한국도로공사에서 수집한 비정형 데이터인 고속도로 VOC 데이터를 이용하여 교통분야에서 사용할 수 있는 감성분석 방법론을 개발하였다. 개발된 감성분석 방법론은 수집된 비정형 데이터에 대한 형태소 분석, 감성사전 구축, 감성 판별 등으로 구성되어 있다. 개발된 방법론은 고속도로 관련 트윗 데이터를 이용하여 검증하였다. 분석 결과, 분석 기간 동안 고속도로와 관련하여 공사, 사고에 대한 정보 전달이 많이 이루어졌음을 짐작할 수 있었다. 또한 공사 및 사고로 인해 발생한 지체에 대하여 이용자들의 불만이 높았던 것으로 판단된다. 결론적으로 SNS 감성분석이 교통분야에서도 의미 있는 정보추출이 가능한 기법임을 확인하였다.

Keywords

References

  1. Bae J. W., Son J. E. and Song M.(2013), "Analysis of Twitter for 2012 South Korea Presidential Election by Text Mining Techniques," The Journal of Intelligence and Information Systems, vol. 19, no. 3, pp.141-156. https://doi.org/10.13088/jiis.2013.19.3.141
  2. Cho H. N., Chung Y. O. and Lee J. D.(2013), "Sentiment Analysis Using News Comments for Public Opinion Mining," Proceedings of KIIS Spring Conference 2013, vol. 23, no. 1, pp.149-150.
  3. Godbole N., Srinivasaiah M. and Skiena S.(2007), "Large-Scale Sentiment Analysis for News and Blogs," Proceedings of the International Conference on Weblogs and Social Media, pp.219-222.
  4. Google Our Planet 2013, Google, https://apac.th inkwithgoogle.com/intl/ko_ALL/, 2016.10.11.
  5. Hong D. P.(2016), Study on the Utilization of Unstructured Data for the Effective Management of Expressway Traffic Information, Ajou University.
  6. IDG Tech Report(2014), Reading emotions in writing -Sentiment Analysis, pp.1-10.
  7. Kim Y. S. and Jeong S. R.(2013), "Intelligent VOC Analyzing System Using Opinion Mining," The Journal of Intelligence and Information Systems, vol. 19, no. 3, pp.113-125. https://doi.org/10.13088/jiis.2013.19.3.113
  8. NH Economics Research Institute(2013), Applica tions and Implications of Big Data, pp.10-19.
  9. Seniment Analysis, Naver, http://terms.naver.com/entry.nhn?docId=2070770&cid=42346&categoryId=42346, 2016.10.11.
  10. Seoul National University IDS Lab, http://kkma.snu.ac.kr/, 2016.10.11.
  11. Yu E. J., Kim Y. S., Kim N. G. and Jeong S. R.(2013), "Predicting the Direction of the Stock Index by Using a Domain-Specific Sentiment Dictionary," The Journal of Intelligence and Information Systems, vol. 19, no. 1, pp.95-110. https://doi.org/10.13088/jiis.2013.19.1.095
  12. Yun H. M., Hong S. G. and Lee T. H.(2016), "Sentiment Analysis on Plant Business of Seawater Desalination in Gijang, Busan," The Korean Association for Local Government Studies Conference Materials, vol. 2015, no. 4, pp.13-20.
  13. Zhuang L., Jing F. and Zhu X. Y.(2006), "Movie review mining and summarization," Proceedings of the 15th ACM international conference on Information and knowledge management, pp.43-50.

Cited by

  1. An Investigation into the Causal Relationship and the Cross Correlation between Apartment House Sales Prices and Real Estate Online News : An Approach to the Sentiment Analysis Using Unstructured Big vol.54, pp.1, 2017, https://doi.org/10.17208/jkpa.2019.02.54.1.131
  2. Generating Traffic Safety Test Scenarios for Automated Vehicles using a Big Data Technique vol.23, pp.6, 2017, https://doi.org/10.1007/s12205-019-1287-4
  3. Social Emotional Opinion Decision with Newly Coined Words and Emoticon Polarity of Social Networks Services vol.11, pp.8, 2017, https://doi.org/10.3390/fi11080165
  4. 트위터 사용자들의 감성을 이용한 사회적 이슈 분석 vol.9, pp.11, 2017, https://doi.org/10.22156/cs4smb.2019.9.11.081
  5. Defining Smart Mobility Service Levels via Text Mining vol.12, pp.21, 2017, https://doi.org/10.3390/su12219293
  6. Comparing Strengths and Weaknesses of Three Approaches in Estimating Social Demands for Local Forest Ecosystem Services in South Korea vol.12, pp.4, 2017, https://doi.org/10.3390/f12040497