DOI QR코드

DOI QR Code

A Study on Effective Sentiment Analysis through News Classification in Bankruptcy Prediction Model

부도예측 모형에서 뉴스 분류를 통한 효과적인 감성분석에 관한 연구

  • 김찬송 (한양대학교 일반대학원 비즈니스 인포매틱스학과) ;
  • 신민수 (한양대학교 경영학부)
  • Received : 2018.01.31
  • Accepted : 2019.01.10
  • Published : 2019.03.31

Abstract

Bankruptcy prediction model is an issue that has consistently interested in various fields. Recently, as technology for dealing with unstructured data has been developed, researches applied to business model prediction through text mining have been activated, and studies using this method are also increasing in bankruptcy prediction. Especially, it is actively trying to improve bankruptcy prediction by analyzing news data dealing with the external environment of the corporation. However, there has been a lack of study on which news is effective in bankruptcy prediction in real-time mass-produced news. The purpose of this study was to evaluate the high impact news on bankruptcy prediction. Therefore, we classify news according to type, collection period, and analyzed the impact on bankruptcy prediction based on sentiment analysis. As a result, artificial neural network was most effective among the algorithms used, and commentary news type was most effective in bankruptcy prediction. Column and straight type news were also significant, but photo type news was not significant. In the news by collection period, news for 4 months before the bankruptcy was most effective in bankruptcy prediction. In this study, we propose a news classification methods for sentiment analysis that is effective for bankruptcy prediction model.

Keywords

OTSBB9_2019_v18n1_187_f0001.png 이미지

Research Model for Sentiment Analysis that is Effective in Bankruptcy Prediction

OTSBB9_2019_v18n1_187_f0002.png 이미지

Data Pre-Processing and Sentiment Dictionary Building Process

OTSBB9_2019_v18n1_187_f0003.png 이미지

Artificial Neural Network Model

OTSBB9_2019_v18n1_187_f0004.png 이미지

Collection Period of News

OTSBB9_2019_v18n1_187_f0005.png 이미지

Sensitivity Graph According to News Collection Period

Types of News Previous Research

OTSBB9_2019_v18n1_187_t0001.png 이미지

Altman's Financial Ratio Variable

OTSBB9_2019_v18n1_187_t0002.png 이미지

Top 20 Words by Frequency

OTSBB9_2019_v18n1_187_t0003.png 이미지

Examples of Corpus-based Sentimental Dictionary Words

OTSBB9_2019_v18n1_187_t0004.png 이미지

The Number and Percentage of News Types

OTSBB9_2019_v18n1_187_t0005.png 이미지

Prediction Accuracy of the News Type to Bankruptcy Prediction

OTSBB9_2019_v18n1_187_t0006.png 이미지

Prediction Sensitivity of the News Type to Bankruptcy Prediction

OTSBB9_2019_v18n1_187_t0007.png 이미지

Prediction Results Using News Gathering Period and Financial Ratios

OTSBB9_2019_v18n1_187_t0010.png 이미지

t-Test Result of News Type Variable

OTSBB9_2019_v18n1_187_t0011.png 이미지

t-Test Result of Financial Ratio Variable

OTSBB9_2019_v18n1_187_t0012.png 이미지

References

  1. Aggarwal, C.C. and C.X. Zhai, Mining Text Data. Springer, New York, 2012.
  2. Altman, E.I., "Financial ratios, discriminant analysis and the prediction of corporate bankruptcy", The Journal of Finance, Vol.23, No.4, 1968, 589-609. https://doi.org/10.1111/j.1540-6261.1968.tb00843.x
  3. Altman, E.I., G. Sabato, and N. Wilson, "The value of non-financial information in small and medium-sized enterprise risk management", Journal of Credit Risk, Vol.2, No.6, 2010, 95-127. https://doi.org/10.21314/JCR.2010.110
  4. An, J.K. and H.W. Kim, "Building a Korean Sentiment Dictionary and Applications of Natural Language Processing", Proceeding of Korea Intelligent Information Systems Society Conference, No.11, 2014, 177-182.
  5. Bang, E.J. and S.T. Kim, "A Study of SNS Sources in Korean Major Newspapers", Journal of Cybercommunication Academic Society, Vol.29, No.4, 2012, 145-189.
  6. Beaver, W.H., "Financial Ratios as Predictors of Failure", Journal of Accounting Research, Vol.4, 1966, 71-111. https://doi.org/10.2307/2490171
  7. Campbell, J., J. Hilscher, J. Szilagyi, "In Search of Distress Risk", Journal of Finance, Vol. 63, No.6, 2008, 2899-2939. https://doi.org/10.1111/j.1540-6261.2008.01416.x
  8. Cho, C.L., Media Writing, Communication Books, Seoul, 2015.
  9. Dave, K., S. Lawrence, and D.M. Pennock, "Mining the peanut gallery : Opinion extraction and semantic classification of product reviews", Proceedings of the 12th International Conference on World Wide Web, 2003, 519-528.
  10. Esuli, A. and F. Sebastiani, "Determining the semantic orientation of terms through gloss classification", Proceedings of the 14th ACM international conference on Information and knowledge management, 2005, 617-624.
  11. Gupta, A., M. Simaan, and M.J. Zaki, "Investigating Bank Failures Using Text Mining", Computational Intelligence (SSCI), 2016.
  12. Jo, N.O. and K.S. Shin, "Bankruptcy prediction modeling Using Qualitative Information Based on Big Data Analytics", Journal of Intelligent and Information Systems, Vol.22, No. 2, 2016, 33-56. https://doi.org/10.13088/jiis.2016.22.2.033
  13. Kim, M.H., H.-Y. Jang, Y.-M. Jo, and, H.P. Shin, "KOSAC : Korean Sentiment Analysis Corpus", Proceeding of Korean Institute of Information Scientists and Engineers Conference, 제6호, 2013, 650-652.
  14. Kim, S.W. and N.G. Kim, "A Study on the Effect of Using Sentiment Lexicon in Opinion Classification", Journal of Intelligent and Information Systems, Vol.20, No.1, 2014, 133-148.
  15. Kuhn, R. and E. Neveu, Political Journalism : New challenges, new practices, Routledg, 2013.
  16. Lu, Y.C., C.H. Shen, and Y.C. Wei, "Revisiting early warning signals of corporate credit default using linguistic analysis", Pacific-Basin Finance Journal, Vol.24, 2013, 1-21. https://doi.org/10.1016/j.pacfin.2013.02.002
  17. Mandel, S., Modern Journalism. Pitman Publishing Corp, New York, 1962.
  18. Miller, G.A., R. Beckwith, C. Fellbaum, D. Gross, and K.J. Miller, "Introduction to wordnet : An on-line lexical database", International Journal of Lexicography, Vol.3, No.4, 1990, 235-244. https://doi.org/10.1093/ijl/3.4.235
  19. Ohlson, J.A., "Financial ratios and the probabilistic prediction of bankruptcy", Journal of Accounting Research, Vol.18, No.1, 1980, 109-131. https://doi.org/10.2307/2490395
  20. Salah, Z., F. Coenen, and D. Grossi, Generating Domain-Specific Sentiment Lexicons for Opinion Mining. Advanced Data Mining and Applications, Springer, Berlin Heidelberg, 2013.
  21. Salgado, S., J. Stromback, T. Aalberg, and F. Esser, Comparing Political Journalism. Routledge, London and New York, 2016.
  22. Seol, J.A., "A Study on Attributes of News and Reports in Social News", Korean Journal of Journalism & Communication Studies, Vol.57, No.6, 2012, 149-175.
  23. Yu, E.J., Y.S. Kim, N.G. Kim, and S.R. Jeong, "Predicting the Direction of the Stock Index by Using a Domain-Specific Sentiment Dictionary", Journal of Intelligent and Information Systems, Vol.19, No.10, 2013, 95-110.) https://doi.org/10.13088/jiis.2013.19.1.095
  24. Zhang, Z., Q. Ye, Z. Zhang, and Y. Li, "Sentiment classification of Internet restaurant reviews written in Cantonese", Expert Systems with Applications, Vol.38, No.6, 2011, 7674-7682. https://doi.org/10.1016/j.eswa.2010.12.147
  25. Zhou, L., "Performance of corporate bankruptcy prediction models on imbalanced dataset : The effect of sampling methods", Knowledge-Based Systems, Vol.41, No.1, 2013, 16-25. https://doi.org/10.1016/j.knosys.2012.12.007
  26. Zmijewski, M.E., "Methodological Issues Related to the Estimation of Financial Distress Prediction Models", Journal of Accounting Research. Vol.22, 1985, 55-82. https://doi.org/10.2307/2490858