Earticle

초록

영어

Bankruptcy prediction has been studied to develop predictive models based on financial variables. Using only financial variables may be insufficient in bankruptcy prediction modeling because they do not reflect the latest information, essentially when using past corporate accounting information. Thus, exploiting qualitative information with quantitative information is required to supplement the limited accounting information. Among big data analytics techniques, text mining is used for processing qualitative information. In this study, we propose an integrated approach for bankruptcy prediction using market sentiment extracted from economic news as qualitative information and financial variables as quantitative information for bankruptcy prediction. Unlike previous sentiment analysis approaches, consideration of topics extracted from economic news in sentiment analysis is included to mitigate the ambiguity of capturing the sentiment for single terms. This study validates the effectiveness of incorporating topic-based market sentiment into the conventional bankruptcy prediction model using financial variables in terms of predictive performance.

목차

Abstract
 Introduction
 Related Work
  Bankruptcy Prediction Modeling
  Business Prediction Modeling Using Big Data Analytics
 Methodology
  Text preprocessing
  Latent semantic analysis
  Sentiment analysis
 Proposed Model
  Topic extraction using LSA
  Sentiment analysis using news topic
 Model Development
  Research data and experiments
  Result and analysis
 Conclusions
 Acknowledgments
 References

저자

• Nam-ok Jo [ Ewha Womans University ]
• Kyung-shik Shin [ Ewha Womans University ]

참고문헌