Sentiment Matters in Stock Market: Construction of Sentiment Index Using Machine Learning
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
This study employs machine learning to analyze news article sentiment, developing a stock market sentiment index (SSI) based on this analysis. By examining the textual data from news articles, which constitute unstructured data, we aimed to capture the prevailing sentiments among market participants across the financial market. Specifically, this study utilizes The BERT model to decipher the psychological sentiment embedded in the articles through its contextualized understanding of the tone and language patterns. The variables tested included the risk aversion estimate, calculated using the VKOSPI and Bekaert’s method for assessing risk aversion. The empirical analysis involving the SSI, VKOSPI, and risk aversion reveals a significant negative impact of SSI on VKOSPI and risk aversion. We further find that the news sentiment index (NSI) and SSI simultaneously exhibit a converging trend.
Abstract
This study employs machine learning to analyze news article sentiment, developing a stock market sentiment index (SSI) based on this analysis. By examining the textual data from news articles, which constitute unstructured data, we aimed to capture the prevailing sentiments among market participants across the financial market. Specifically, this study utilizes The BERT model to decipher the psychological sentiment embedded in the articles through its contextualized understanding of the tone and language patterns. The variables tested included the risk aversion estimate, calculated using the VKOSPI and Bekaert’s method for assessing risk aversion. The empirical analysis involving the SSI, VKOSPI, and risk aversion reveals a significant negative impact of SSI on VKOSPI and risk aversion. We further find that the news sentiment index (NSI) and SSI simultaneously exhibit a converging trend.
참고문헌 (20)
- Bekaert, G., "Risk, uncertainty and monetary policy", Journal of Monetary Economics, 60, pp.771~788 (2013)
- Breiman, L., "Random forests", Machine learning, 45, pp.5~32 (2001)
- Chen, T., "XGBoost: A scalable tree boosting system", Proceedings of the 22nd International Conference on Knowledge Discovery and Data Mining, pp.785~794 (2016)
- Choi, H., "Explanation and empirical analysis of the volatility index (VKOSPI)", Key Data on KRX Market, 43~56 (2009)
- Hearst, M. A., "Support vector machines", IEEE Intelligent Systems and Their Applications, 13, pp.18~28 (1998)
- Hull, J. C., "Options, futures, and other derivatives" (2016), Pearson Education India
- Kowsari, K., "Text classification algorithms : A survey", Information, 10, pp.150~ (2019)
- Ke, G., "LightGBM : A highly efficient gradient boosting decision tree", Advances in Neural Information Processing Systems, 30, pp.3146~3154 (2017)
- Kleinbaum, D. G., "Logistic regression" (2002), Springer-Verlag
- Lang, G. E., "The battle for public opinion: The president, the press, and the polls during Watergate" (1983), Columbia University Press
- Noelle-Neumann, E., "The spiral of silence : A theory of public opinion", Journal of Communication, 24, pp.43~51 (1974)
- Seo, B., "Measuring news sentiment of Korea using transformer", Korean Economic Review, 40, pp.149~176 (2024)
- Shapiro, A. H., "Measuring news sentiment", Journal of econometrics, 228, pp.221~243 (2022)
- 김세완, "심리변수가손해보험소비자의의사결정에미치는영향:위험회피수준및댓글감성을중심으로", 보험금융연구, 32, pp.65~93 (2021)
- 박변갑, "텍스트마이닝 분석을 통한 공간의 의미 표출에 관한 연구 - 교량 자살 빅데이터를 중심으로", 한국공간디자인학회 논문집, 16, pp.181~190 (2021)
- 서범석, "기계학습을 이용한 뉴스심리지수 (NSI) 의작성과 활용", BOK 국민계정리뷰, pp.68~90 (2022)
- 송민채, "뉴스기사를 이용한 소비자의 경기심리지수 생성", 지능정보연구, 23, pp.1~27 (2017)
- 윤태일, "텍스트마이닝 기법을 활용한 신입생의 대학생활 경험 분석", 인문사회 21, 12, pp.279~294 (2021)
- 정민경, "텍스트 마이닝 기법을 활용한 COVID-19 발생 이전· 이후의 배달주문플랫폼 서비스에 대한 주요 토픽 분석", 지역산업연구, 44, pp.283~305 (2021)