Journal of the Korean Society for information Management (정보관리학회지)

Korean Society for Information Management (한국정보관리학회)
권호 표지
DOI QR코드

DOI QR Code

Analyzing Topic Trends and the Relationship between Changes in Public Opinion and Stock Price based on Sentiment of Discourse in Different Industry Fields using Comments of Naver News

네이버 뉴스 댓글을 이용한 산업 분야별 담론의 감성에 기반한 주제 트렌드 및 여론의 변화와 주가 흐름의 연관성 분석

  • 오찬희 (성균관대학교 문헌정보학과) ;
  • 김규리 (성균관대학교 문헌정보학과) ;
  • 주영준 (연세대학교 문헌정보학과)
  • Received : 2022.02.21
  • Accepted : 2022.03.14
  • Published : 2022.03.30
Download PDF
⟨ Previous Next ⟩

Abstract

In this study, we analyzed comments on news articles of representative companies of the three industries (i.e., semiconductor, secondary battery, and bio industries) that had been listed as national strategic technology projects of South Korea to identify public opinions towards them. In addition, we analyzed the relationship between changes in public opinion and stock price. 'Samsung Electronics' and 'SK Hynix' in the semiconductor industry, 'Samsung SDI' and 'LG Chem' in the secondary battery industry, and 'Samsung Biologics' and 'Celltrion' in the bio-industry were selected as the representative companies and 47,452 comments of news articles about the companies that had been published from January 1, 2020, to December 31, 2020, were collected from Naver News. The comments were grouped into positive, neutral, and negative emotions, and the dynamic topics of comments over time in each group were analyzed to identify the trends of public opinion in each industry. As a result, in the case of the semiconductor industry, investment, COVID-19 related issues, trust in large companies such as Samsung Electronics, and mention of the damage caused by changes in government policy were the topics. In the case of secondary battery industries, references to investment, battery, and corporate issues were the topics. In the case of bio-industries, references to investment, COVID-19 related issues, and corporate issues were the topics. Next, to understand whether the sentiment of the comments is related to the actual stock price, for each company, the changes in the stock price and the sentiment values of the comments were compared and analyzed using visual analytics. As a result, we found a clear relationship between the changes in the sentiment value of public opinion and the stock price through the similar patterns shown in the change graphs. This study analyzed comments on news articles that are highly related to stock price, identified changes in public opinion trends in the COVID-19 era, and provided objective feedback to government agencies' policymaking.

본 연구에서는 대한민국 정부가 지정한 국가전략기술 사업인 반도체, 이차전지, 바이오 산업에 대한 여론을 파악하고 여론의 변화와 주가 흐름의 연관성을 분석하기 위해 각 산업별 대표 기업에 대한 기사의 댓글을 분석하였다. 반도체 산업에서 '삼성전자', 'SK하이닉스', 이차전지 산업에서 '삼성SDI', 'LG화학', 바이오 산업에서 '삼성바이오로직스', '셀트리온'을 선정하여 이를 제목에 포함하고 있는 2020년 1월 1일부터 2020년 12월 31일까지 발행된 네이버 뉴스 기사의 댓글 47,452개를 수집하고 분석하였다. 먼저, 해당 댓글을 긍정, 중립, 부정의 감성으로 나누고 각 감성 그룹에서의 시간의 흐름에 따른 댓글의 동적인 주제를 분석하여 각 산업별 여론의 트렌드를 파악하였다. 분석 결과 반도체 산업 분야의 경우 투자, 코로나19관련 이슈, 삼성전자라는 대기업에 대한 신뢰, 정부 정책 변화로 인한 타격에 대한 언급이 주제 토픽으로 나타났다. 이차전지 산업체의 경우 투자, 배터리, 기업 이슈에 대한 언급이 주제 토픽으로 나타났다. 바이오 산업체의 경우 투자, 코로나19 관련 이슈 및 기업 이슈에 대한 언급이 주제 토픽으로 나타났다. 다음으로, 댓글의 감성이 실제 주가와 연관성이 있는지를 알아보고자 각 대표 기업 별 주가의 변화와 댓글의 감성 점수 변화를 시각적 분석기법을 이용하여 비교 분석하였다. 분석 결과, 댓글의 감성 점수와 주가의 변화 흐름이 매우 유사하게 나타남을 통해 여론의 감성 점수 변화와 주가의 흐름에는 연관성이 있음을 확인하였다. 본 연구는 주가와의 연관성이 높은 뉴스 기사 댓글을 분석했다는 점, 수집 시기를 코로나19로 선정하여 코로나19라는 특수한 상황에서의 여론 트렌드 변화를 파악했다는 점, 국가전략기술제도에 속하는 산업 기업에 대한 여론을 분석하여 정부기관의 관련 정책 제정에 객관적인 근거를 제공하였다는 점에서 의의를 지닌다.

Keywords

Acknowledgement

이 논문은 2021년 대한민국 교육부와 한국연구재단의 지원을 받아 수행된 연구임(NRF-2021S1A5C2A02088387).

References

  1. Bae, Ji Yang (2009). The influence of online news replies on netizens' CSR perception, attitude, purchase intention, and word of mouth intention: focusing on corporate social responsibility activity. The Korean Journal of Advertising, 20(5), 7-37.
  2. Jang, Eun A, Choi, Hoe Ryeon, & Lee, Hong Chul (2020). Stock prediction using combination of BERT sentiment analysis and macro economy index. Journal of the Korea Society of Computer and Information, 25(5), 47-56. https://doi.org/10.9708/jksci.2020.25.05.047
  3. Jo, Su Young, Jang, Hye Ji, & Kwon, Gu Min (2012). Netizens' reactions toward corporate crises: content analysis of crisis news stories and online readers' comments. Korean Journal of Journalism & Communication Studies, 56(4), 311-338.
  4. Kim, Da Ye & Lee, Young Gin (2018). News based stock market sentiment lexicon acquisition using Word2Vec. The Korea Journal of BigData, 3(1), 13-20. https://doi.org/10.36498/kbigdt.2018.3.1.13
  5. Kim, Dong Young, Park, Je Won, & Choi, Jae Hyeon (2014). A comparative study between stock price prediction models using sentiment analysis and machine learning based on SNS and news articles. Journal of Information Technology Services, 13(3), 221-233. https://doi.org/10.9716/KITS.2014.13.3.221
  6. Kim, Gun Tae & Hwang, Su Seong (2015. May). Korea daily newspaper impact on the priceearnings ratio and investment outcome of investors. Conference on The Korean Finance Association, 1810-1841
  7. Kim, Il Hwan (2019). Newspaper big data and text mining for digital humanities. the society of chung-ang lang. & Lit, 78 41-62. https://doi.org/10.15565/jll.2019.06.78.41
  8. Kim, Ji Ryong & Han, Eun Kyung (2019). A study on corporate reputation and profitability focus on online news and comments. Journal of Digital Convergence, 17(9), 399-406. https://doi.org/10.14400/JDC.2019.17.9.399
  9. Kim, Se Wan, Park, Ji Won, Kim, Young Min, & Ham, Hee Kyung (2020). Asymmetric effect of social sentimental on an individual stock price return. Information Systems Review, 22(4), 59-74. https://doi.org/10.14329/isr.2020.22.4.059
  10. Kim, Won Jung & Han, Jeong Ho (2016). The effects of posted comments tagged to newspaper articles to readers' perceived crisis responsibility and their purchase intention. The Korean Journal of Advertising, 27(8), 109-137. https://doi.org/10.14377/KJA.2016.11.30.109
  11. Kim, Yu Shin, Kim, Nam Gyu, & Jeong, Seung Ryeol (2012). Stock-index invest model using news big data opinion mining. Korea Intelligent Information Systems Society, 18(2), 143-156. https://doi.org/10.13088/jiis.2012.18.2.143
  12. Korea Exchange. (2020. August 10). Index composition. Available: http://www.krx.co.kr
  13. Lee, Byung Hyun, Choi, Il Young, Jeon, Jeong Woo, Choi, Ikwon, & Kim, Jae Kyung (2020). A study on corporate reputation and profitability using online news text mining. Korean Management Science Review, 37(4), 55-66. https://doi.org/10.7737/KMSR.2020.37.4.055
  14. Lee, Mi Kyung, Choi, In Ho, & Jeong, Se Hoon (2013). The effect of positive and negative comments on consumers' attitudes, norms, and purchasing behavior on corporate Facebook. Korean Society for Journalism and Communication Studies, 57(4), 51-71.
  15. Ministry of Economy and Finance (2021). It's going to change like this starting 2022. Available: https://whatsnew.moef.go.kr/mec/ots/dif/main.do
  16. Nam, Dal Woo, Park, Jin Woo, Kim, Min Kyung, Jo, Hyeon, & Kim, Seong Hee (2012). A study about correlation between collective intelligence on the internet stock message board and stock market. Korea Internet Electronic Commerce Association, 12(2), 149-164.
  17. Park, Eun Jeong & Cho, Sung Zoon (2014). KoNLPy: Korean natural language processing in python. Proceedings of the 26th Annual Conference on Human and Cognitive Language Technology, 4-7.
  18. Park, Mi Hwa & Kim, Sol (2017). A study on analysis of korean society's xenophobia towards korean-chinese through comments of online news: focused on before and after oh won-chun news report. Multiculture & Peace, 11(3), 92-117. https://doi.org/10.22446/mnpisk.2017.11.3.005
  19. Park, Sang Min, Na, Cheol Won, Choi, Min Seong, Lee, Da Hee, & On, Byeong Won (2018). KNU Korean sentiment lexicon: Bi-LSTM-based method for building a Korean sentiment lexicon. Journal of Intelligence and Information Systems, 24(4), 219-240. https://doi.org/10.13088/jiis.2018.24.4.219
  20. Park, Seong Woo (2021. December 31). New 'national strategic technology' such as semiconductors and batteries... Double the investment deduction for large companies↑. Chosunbiz, Available: https://biz.chosun.com/policy/policy_sub/2021/12/31/3RAH5ZVKWNFDDCXCRGNKPWE6PU/
  21. Park, Seong Wook, Kwon, Oh Byeong, & Na, Hyung Jong (2017). The effect of social media related to informal data of big data on sales. Korea Accounting Information Association, 35(2), 321-342.
  22. Son, Il Sun & Yang, Yeon Ho (2020, October 8). Based on the stock transfer tax of 300 million won...It was called a "two-year postponement" due to the opposition of Donghak Ant. Maeil Business Newspaper, Available: https://www.mk.co.kr/news/economy/view/2020/10/1033433/
  23. Yang, Hye Seung (2008). The effects of the opinion and quality of user postings on internet news readers' attitude toward the news issue. Korean Society For Journalism And Communication Studies, 52(2), 254-281.
  24. Zhu, Yong Jun, Kim, Dong Hoon, Lee, Chang Ho, & Lee, Yong Jeong (2019). Investigating major topics through the analysis of depression-related facebook group posts. Journal of the Korean Library and Information Science, 53(4), 171-187. https://doi.org/10.4275/KSLIS.2019.53.4.171
  25. Blei, D. M. & Lafferty, J. D. (2006). Dynamic Topic Models. Proceedings of the 23rd International Conference on Machine Learning, 113-120.
  26. Fu, T. C., Lee, K. K., Sze, D., Chung, F. L., & Ng, C. M. (2008). Discovering the correlation between stock time series and financial news. Proceeding of IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology, 880-883. https://doi.org/10.1109/WIIAT.2008.228
  27. Keim, D., Andrienko, G., Fekete, J. D., Gorg, C., Kohlhammer, J., & Melancon, G. (2008). Visual analytics: definition, process, and challenges. In Information Visualization, 154-175. https://doi.org/10.1007/978-3-540-70956-5_7
  28. Muthukadan, B. (2018). Selenium 3.141.0 [Online App]. Available: https://selenium-python.readthedocs.io/
  29. Prabhakaran, S. (2018). Topic Modeling with Gensim (Python). Available: https://www.machinelearningplus.com/nlp/topic-modeling-gensim-python/
  30. Rehurek, R. & Sojka, P. (2011). Gensim-python framework for vector space modelling. NLP Centre, Faculty of Informatics, Masaryk University, Brno, Czech Republic, 3(2).
  31. Richardson, L. (2019). BeautifulSoup (4.8.1) [Online App]. Available: https://beautiful-soup-4.readthedocs.io/
  32. Tetlock, P. C. (2007), Giving content to investor sentiment: The role of media in the stock market. The Journal of Finance, 62(3), 1139-1168. https://doi.org/10.1111/j.1540-6261.2007.01232.x
  33. Thomas, J. J. & Cook, K. A. (2006). A visual analytics agenda. IEEE Computer Graphics and Applications, 26(1), 10-13. https://doi.org/10.1109/MCG.2006.5
  34. Wang, C. & Blei, D. M. (2011). Collaborative topic modeling for recommending scientific articles. In Proceedings of the 17th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 448-456. https://doi.org/10.1145/2020408.2020480