Journal of Digital Convergence (디지털융복합연구)

The Society of Digital Policy and Management (한국디지털정책학회)
권호 표지
DOI QR코드

DOI QR Code

Application of Sentiment Analysis and Topic Modeling on Rural Solar PV Issues : Comparison of News Articles and Blog Posts

감성분석과 토픽모델링을 활용한 농촌태양광 관련 이슈 연구 : 언론 기사와 블로그 포스트 비교

  • Ki, Jaehong (Graduate School of Environmental Studies, Seoul National University) ;
  • Ahn, Seunghyeok (Environmental Planning Institute, Seoul National University)
  • 기재홍 (서울대학교 환경대학원) ;
  • 안승혁 (서울대학교 환경계획연구소)
  • Received : 2020.06.30
  • Accepted : 2020.09.20
  • Published : 2020.09.28
Download PDF
⟨ Previous Next ⟩

Abstract

News articles and blog posts have influence on social agenda setting and this study applied text mining on the subject of solar PV in rural area appeared in those media. Texts are gained from online news articles and blog posts with rural solar PV as a keyword by web scrapping, and these are analysed by sentiment analysis and topic modeling technique. Sentiment analysis shows that the proportion of negative texts are significantly lower in blog posts compared to news articles. Result of topic modeling shows that topics related to government policy have the largest loading in positive articles whereas various topics are relatively evenly distributed in negative articles. For blog posts, topics related to rural area installation and environmental damage are have the largest loading in positive and negative texts, respectively. This research reveals issues related to rural solar PV by combining sentiment analysis and topic modeling that were separately applied in previous studies.

사회적 의제 설정 영향력을 지닌 미디어인 언론 기사와 블로그 포스트에서 농촌태양광이 어떻게 다루어지고 있는지 분석하기 위해 텍스트 마이닝 방법을 활용하였다. 농촌태양광을 키워드로 웹스크래핑을 통해 기사와 블로그 포스트의 텍스트 자료를 수집하고, 이에 대해 감성분석과 토픽모델 기법을 적용하여 연구를 수행했다. 감성분석 결과 농촌태양광에 대한 텍스트에서 두 매체 모두 긍정적인 입장을 가지는 비율이 높았는데, 블로그의 경우 기사에 비해 부정적인 내용을 담은 텍스트의 비중이 훨씬 낮은 것을 확인할 수 있었다. 그리고 토픽모델링 결과로 긍정 기사는 정부의 보급계획 관련 토픽들의 비중이 컸고, 부정 기사는 다양한 토픽들의 비중이 고르게 분포하였다. 블로그는 긍정 포스트의 경우 농촌 지역 설치 관련 토픽들이, 부정 포스트는 환경 피해 관련 토픽들이 가장 큰 부분을 차지했다. 기존에 별개로 이루어지던 감성분석과 토픽모델링을 결합하는 연구 방식을 제시함으로써 농촌태양광에 대한 이슈를 효과적으로 파악할 수 있었다.

Keywords

References

  1. MOTIE & KEA. (2019). New & Renewable Energy White Paper. Retrieved from https://www.knrec.or.kr/pds/pds_read.aspx?no=291&searchfield=&searchword=&page=1
  2. M. L. Park, S. W. Shin, S. D. Oh, & S. H. Kang. (2019). A Study on the Direction of Resident Acceptability for Photovoltaic System in Rural region - A Case of the Rural Village in Munback-Myeon, Jincheon-Gun, Chungbuk. Journal Of The Korean Institute Of Rural Architecture, 21(3), 77-84. DOI : 10.14577/kirua.2019.21.3.77
  3. S. S. Jung. (2017). Study on Measures to Improve Residents' Acceptance for Renewable Energy. Ulsan : Korea Energy Economics Institute. Retrieved from http://www.keei.re.kr/main.nsf/index.html?open&p=%2Fweb_keei%2Fd_results.nsf%2Fmain_all%2F95EDFE7DC198969F492583CB002F18FC&s=%3FOpenDocument%26menucode%3DS0%26category%3D%25EA%25B8%25B0%25EB%25B3%25B8%25EC%2597%25B0%25EA%25B5%25AC
  4. S. S. Jung & S. M. Lee. (2018). Study on the Benefit Sharing System to Improve Acceptance for Renewable Energy. Ulsan : Korea Energy Economics Institute. Retrieved from http://www.keei.re.kr/main.nsf/index.html?open&p=%2Fweb_keei%2Fd_results.nsf%2Fmain_all%2F95EDFE7DC198969F492583CB002F18FC&s=%3FOpenDocument%26menucode%3DS0%26category%3D%25EA%25B8%25B0%25EB%25B3%25B8%25EC%2597%25B0%25EA%25B5%25AC
  5. Y. J. Kim, S. S. Kim, K. S. Chae, D. S. Seo, J. Y. Park, S. H. Song & S. M. Choo. (2018). Study on Problems and Measures to Improve the Diffusion of Rural Solar Energy. Naju : Korea Rural Economic Institute. Retrieved from http://www.krei.re.kr/krei/researchReportView.do?key=67&pageType=010101&biblioId=519732&pageUnit=10&searchCnd=all&searchKrwd=%EB%86%8D%EC%B4%8C%20%ED%83%9C%EC%96%91%EA%B4%91&pageIndex=1&engView=
  6. C. S. Jang & S. K. Kim. (2017). A Study on the Stakeholders Perception Type on the Location of the Solar Light Power Generation Facility: Case of SeoCheon Province. Journal of local government studies, 29(3), 113-133. DOI : 10.9727/jmsk.2016.29.3.113
  7. S. A. Park, S. J. Yun. (2018). Opposition to and Acceptance of Siting Solar Power Facilities from the Place Attachment Viewpoint. ECO 22(2), 267-317. DOI : 10.16974/STLR.2016.22.2.007
  8. D. G. Lee. (2019). Inter-Media Agenda Setting Between Daily Newspapers and Blogs: Content Analysis of Choi Soon-sil Gate. The Journal of Political Science & Communication, 22(2), 53-90. DOI : 10.35731/kpca.2015..39.003
  9. H. J. Ahn & Y. Ha. (2019). Analysis of the Relationship between the Type of Experience and Blog Texts. The Journal of Korean Institute of Information Technology, 15(2), 131-140. DOI : 10.14801/jkiit.2017.15.2.131
  10. S. Kang & Y. Shon. (2020). Study on the Phenomenon of Early Childhood Private Education through Topic Modeling Analysis: Focusing on Domestic Newspaper Articles and Blogs. Journal of Future Early Childhood Education, 27(1), 177-199. DOI : 10.22155/JFECE.27.1.177.199
  11. T. D. Lee, S. Lee, & C. Oh. (2017). A Comparative Analysis of Nuclear Energy Issue Frames in Press Releases and News Articles : A Topic Modeling Approach. Journal of Communication Science, 17(3), 172-229. DOI : 10.14696/jcs.2017.09.17.3.172
  12. G. J. Yoo & E. A. Kim. (2019). A Study on the Morpheme and Emotional Analysis of Newspaper Articles on Children's Right to Play. The Journal of Korea Open Association for Early Childhood Education, 24(5), 109-132. DOI : 10.20437/KOAECE24-5-06
  13. S. B. Joo. (2019). Sentimental Analysis of Crime News Data-Focused on the Comparison before and after Regulation of Media Report. Korean Criminal Psychology Review, 15, 127-140. Retrieved from http://scholar.dkyobobook.co.kr/searchDetail.laf?barc ode=4010027331317
  14. S. Shin & H. Kim. (2019). A Proposal of Research Method for Measuring Marketing Communication Effect: Analysis of Image of "National Fitness Award" Project through LDA-based Topic Modeling. Korean Society For Sport Management, 24(6), 48-62. DOI : 10.31308/KSSM.24.6.4
  15. J. H. Lee, I. S. Lee, K. S. Jung, B. H. Chae, & J. Y. Lee. (2017). Patents and Papers Trends of Solar-Photovoltaic(PV) Technology using LDA Algorithm. Journal of Digital Convergence, 15(9), 231-239. DOI : 10.14400/JDC.2017.15.9.231
  16. R. Mitchell. (2018). Web Scraping with Python: Collecting More Data from the Modern Web, 2nd Edition. Sebastopol, CA : O'Reilly Media. Retrieved from https://www.oreilly.com/library/view/web-scraping-with/9781491985564/
  17. D. Sarkar. (2019). Text Analytics with Python: A Practitioner's Guide to Natural Language Processing. Berkeley, CA : Apress. DOI : 10.1007/978-1-4842-4354-1
  18. K. A. Kim & J. H. Ku. (2017). A Study on the Change of the View of Love using Text Mining and Sentiment Analysis. Journal of Digital Convergence, 15(2), 285-294. DOI : 10.14400/JDC.2017.15.2.285
  19. B. Burscher, R. Burscher, & C. H. de Vreese. (2016). Frames Beyond Words: Applying Cluster and Sentiment Analysis to News Coverage of the Nuclear Power Issue. Social Science Computer Review, 34(5), 530-545. DOI : 10.1177/0894439315596385
  20. S. Y. Cho & E. P. Hong. (2019). A Study on the Polarity of Apartment Price News Using Big Data Analysis Method. Journal of Digital Convergence, 17(9), 47-54. DOI : 10.14400/JDC.2019.17.9.047
  21. K. Sheshadri, N. Ajmeri & J. Staddon. (2017, August). No (Privacy) News is Good News: An Analysis of New York Times and Guardian Privacy News from 2010-2016. 2017 15th Annual Conference on Privacy, Security and Trust (PST). (pp. 159-168). Calgary, AB : IEEE. DOI : 10.1109/PST.2017.00027
  22. S. J. Kim, J. E. Kim, W. Y. Seong & Y. H. Kim. (2019). Design of Video Advertisement Analysis via Analysis of Internet Term Sensitivity. Journal of KIISE, 46(9), 919-925. DOI : 10.5626/JOK.2019.46.9.919
  23. Y. H. Lim & H. B. Kim. (2019). A study on the sentiment analysis using big data of hotels online review. Korean Journal of Hospitality and Tourism 28(7), 105-123. DOI : 10.24992/KJHT.2019.10.28.07.105
  24. J. S. Park & J. S. Lee. (2019). 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 Data of Online News Articles. Journal of Korea Planning Association 54(1), 131-147. DOI : 10.17208/jkpa.2019.02.54.1.131
  25. S. H. Seo & J. T. Kim. (2016). Deep Learning-Based Sentiment Analysis Research Trend. Journal of Korea Multimedia Society 20(3), 8-22. Retrieved from http://www.dbpia.co.kr.libproxy.snu.ac.kr/journal/articleDetail?nodeId=NODE07053234&language=ko_KR
  26. B. Tsolmon & G. S. Lee. (2017). Topic Model Reflecting User Behavior and Time Analysis for Extracting Disaster Events from Social Data. Information and Communications Magazine, 34(6), 43-50. Retrieved from http://www.dbpia.co.kr/journal/articleDetail?nodeId=NODE07179145
  27. J. H. Choi, H. S. Lee, & E. H. Jin. (2019). A Topic Modeling Analysis of the News Topic on the 4th Industrial Revolution in Korea: Focusing on the Difference by Media Type and Each Major Period. Journal of Cybercommunication Academic Society, 36(2), 173-219. DOI : 10.36494/JCAS.2019.06.36.2.173
  28. S. S. Lee, I. H. Yoo & J. H. Kim. (2020). An analysis of public perception on Artificial Intelligence(AI) education using Big Data: Based on News articles and Twitter. Journal of Digital Convergence, 18(6), 9-16. DOI : 10.14400/JDC.2020.18.6.009
  29. S. H. Noh. (2020). Analysis of Issues Related to Artificial Intelligence Based on Topic Modeling. Journal of Digital Convergence, 18(5), 75-87. DOI : 10.14400/JDC.2020.18.5.075
  30. S. M. Lee & S. G. Hong. (2020). Policy Agenda Proposals from Text Mining Analysis of Patents and News Articles. Journal of Digital Convergence, 18(3), DOI : 10.14400/JDC.2020.18.3.001
  31. S. Y. Choi & E. J. Ko. (2019). Analysis of Korean Journal of Journalism & Communication Studies from 1960 to 2018 using Metadata with Dynamic Topic Modeling. Korean Journal of Journalism & Communication Studies, 63(4), 7-42. DOI : 10.20879/kjjcs.2019.63.4.001
  32. B. Bengfort, R. Bilbro, & T. Ojeda. (2018). Applied Text Analysis with Python: Enabling Language-Aware Data Products with Machine Learning. Sebastopol, CA : O'Reilly Media. Retrieved from https://www.oreilly.com/library/view/applied-text-an alysis/9781491963036/
  33. P. Singh. (2018). Machine Learning with PySpark: With Natural Language Processing and Recommender Systems. Berkeley, CA : Apress. DOI : 10.1007/978-1-4842-4131-8
  34. J. G. Shin. (2020). Analysis regarding Complaints of Courier Consumers and Workers in the Parcel Delivery Service by using Topic Model. Journal of Convergence for Information Technology, 10(2), 39-48. DOI : 10.22156/CS4SMB.2020.10.02.039