The Journal of Society for e-Business Studies (한국전자거래학회지)

Society for e-Business Studies (한국전자거래학회)
권호 표지
DOI QR코드

DOI QR Code

Stock Price Prediction Using Sentiment Analysis: from "Stock Discussion Room" in Naver

SNS감성 분석을 이용한 주가 방향성 예측: 네이버 주식토론방 데이터를 이용하여

  • Kim, Myeongjin (Department of Industrial Engineering(ITM program), Seoul National University of Science and Technology) ;
  • Ryu, Jihye (Department of Industrial Engineering(ITM program), Seoul National University of Science and Technology) ;
  • Cha, Dongho (Headquarter of Multi-Solution, KB Asset Management) ;
  • Sim, Min Kyu (Department of Industrial Engineering, Seoul National University of Science and Technology)
  • Received : 2020.09.09
  • Accepted : 2020.11.03
  • Published : 2020.11.30
Download PDF
⟨ Previous Next ⟩

Abstract

The scope of data for understanding or predicting stock prices has been continuously widened from traditional structured format data to unstructured data. This study investigates whether commentary data collected from SNS may affect future stock prices. From "Stock Discussion Room" in Naver, we collect 20 stocks' commentary data for six months, and test whether this data have prediction power with respect to one-hour ahead price direction and price range. Deep neural network such as LSTM and CNN methods are employed to model the predictive relationship. Among the 20 stocks, we find that future price direction can be predicted with higher than the accuracy of 50% in 13 stocks. Also, the future price range can be predicted with higher than the accuracy of 50% in 16 stocks. This study validate that the investors' sentiment reflected in SNS community such as Naver's "Stock Discussion Room" may affect the demand and supply of stocks, thus driving the stock prices.

주식의 가격을 이해하고 예측하기 위해서 활용되는 데이터의 범위는 기존의 정형화된 데이터에서 비정형화된 다양한 종류의 데이터로 확대되고 있다. 본 연구는 SNS에서 수집된 댓글 데이터가 주식의 미래 가격의 변동에 영향을 미치는지를 조사한다. 가장 많은 주식투자자가 참여하는 커뮤니티인 네이버 주식토론방에서 20개 종목에 대한 6개월 간의 댓글 데이터를 수집하여, 이들 데이터가 1시간 후의 가격 변동의 방향과 가격 변동의 폭에 대한 예측력을 가지는지 조사한다. 예측 관계는 LSTM과 CNN등의 딥뉴럴네트워크 기법을 활용하여 모델링하였다. 20개 종목에 대해 조사하여 13개 종목에서 미래의 주가 이동 방향을 50% 이상의 정확도로 예측할 수 있다는 결과를 얻었고, 16개 종목에서 미래의 주가 변동폭을 50% 이상의 정확도로 예측할 수 있다는 결과를 얻었다. 본 연구는 네이버 주식토론방과 같은 SNS에서 형성된 여론이 주식 종목의 수급에 영향을 주어 가격의 변동 요인으로도 작용할 수 있다는 점을 확인한다.

Keywords

References

  1. Hochreiter, S. and Schmidhuber, J., "Long short-term memory," Neural computation, Vol. 9, No. 8, pp. 1735-1780, 1997. https://doi.org/10.1162/neco.1997.9.8.1735
  2. Hong, S. H., "A study on stock price prediction system based on text mining method using LSTM and stock market news, Journal of Digital Convergence, Vol. 18, No. 7, pp. 223-228, 2020. https://doi.org/10.14400/jdc.2020.18.7.223
  3. Jeong, J. S., Kim, D. S., and Kim, J. W., "Influence analysis of Internet buzz to corporate performance: Individual stock price prediction using sentiment analysis of online news," Korea intelligent information Systems Society, Vol. 21, No. 4, pp. 37-51, 2015. https://doi.org/10.13088/jiis.2015.21.4.037
  4. Kang, Y. J. and Jang, W. W., "The FiveFactor Asset Pricing Model: Applications to the Korean Stock Market," Eurasian Studies, Vol. 13, No. 2, pp. 155-180, 2016. https://doi.org/10.31203/aepa.2016.13.2.009
  5. Kim, D. H., "Asset Pricing Model in Korean Stock Market," Association of financial engineering, Vol. 13, No. 2, pp. 87-119, 2014.
  6. Kim, D. S., Kim, K. T., and Kim, J. W., "Character-based multi-category sentiment analysis on social media using deep learning algorithms," Korean Institute Of Industrial Engineers, Vol. 2017, No. 4, pp. 5082-5084, 2017.
  7. Kim, D. Y. and Lee, Y. I., "News based Stock Market Sentiment Lexicon Acquisition Using Word2Vec," The Korea Journal of BigData, Vol. 3, No. 1, pp. 13-20, 2018. https://doi.org/10.36498/kbigdt.2018.3.1.13
  8. Kim, D. Y., Park, J. W., and Choi, J. H., "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, Vol. 13, No. 3, pp. 221-233, 2014 https://doi.org/10.9716/KITS.2014.13.3.221
  9. Kim, H, G., Kim, S. D., and Kim, H. W., "A Case Study on the Establishment of an Equity Investment Optimization Model based on FinTech: For Institutional Investors," Korea Knowledge Management Society, Vo. 19, No.1, pp. 97-118, 2018.
  10. Kim, J. Y. and Kim, C. S., "An Analysis on Mediating Effect of Participant Activity in Investment Crowdfunding," The Journal of Society for e-Business Studies, Vol. 25, No. 1, pp. 65-82, 2020. https://doi.org/10.7838/JSEBS.2020.25.1.065
  11. Kim, Y. S., Kim, N. G., and Jeong, S. R., "Stock-Index Invest Model Using News Big Data Opinion Mining," Journal of Intelligence and Information Systems, Vol. 18, No. 2, pp. 143-156, 2012. https://doi.org/10.13088/JIIS.2012.18.2.143
  12. Lee, H. J., "Analysis of News Big Data for Deriving Social Issues in Korea," The Journal of Society for e-Business Studies, Vol. 24, No. 3, pp. 163-182, 2019.
  13. Lee, M. S. and Ahn, H. C., "A Time Series Graph based Convolutional Neural Network Model for Effective Input Variable Pattern Learning: Application to the Prediction of Stock Market," Korea intelligent information Systems Society, Vol. 24, No. 1, pp. 167-181, 2018.
  14. Park, H. J., Song, M. C., and Sim, K. S., "Sentiment Analysis of Korean Reviews Using CNN-Focusing on Morpheme Embedding," Korea intelligent information Systems Society, Vol. 24, No. 2, pp. 59-83, 2018.
  15. Seo, I. S., Yeo, S. S., and Kang, H. J., "A Study on the Suggestion of Domestic Stock Market Analysis Scheme using Big Data," Korean Institute of information technology, Vol. 2014, No. 5, pp. 550-554, 2014.
  16. Son, S. H., Kim, T. H., and Yoon, B. H., "Testing the Linear Asset Pricing Models in the Korean Stock Market," Korean Journal of Financial Studies, Vol. 38, No. 4, pp. 547-568, 2009.
  17. Song, S. H., Kim, J. H., Kim, H. S., Park, J. S., and Kang, P. S., "Development of Early Warning Model for Financial Firms Using Financial and Text Data: A Case Study on Insolvent Bank Prediction," Journal of the Korean Institute of Industrial Engineers, Vol. 45, No. 3, pp. 248-259, 2019. https://doi.org/10.7232/JKIIE.2019.45.3.248
  18. Suh, M. S. and Kim, D. H., "A Study on the Changing Direction of FinTech Service Model based on Big Data," The ebusiness studies, Vol. 20, No. 2, pp. 195-213, 2019.
  19. Yoo, H. S., "What are the core competitiveness and alternative data in the digital age?," Available at: https://2e.co.kr/news/articleView.html?idxno=209967, 2019.

Cited by

  1. 딥러닝 기반의 분할과 객체탐지를 활용한 도로균열 탐지시스템 개발 vol.26, pp.1, 2020, https://doi.org/10.7838/jsebs.2021.26.1.093
  2. 2단계 k-평균 군집화를 활용한 한류컨텐츠 기업 주가 예측 연구 vol.12, pp.7, 2020, https://doi.org/10.15207/jkcs.2021.12.7.169