재무분야 감성사전 구축을 위한 자동화된 감성학습 알고리즘 개발
Developing the Automated Sentiment Learning Algorithm to Build the Korean Sentiment Lexicon for Finance
0
조회
0
다운로드
3
인용
0
참고문헌
키워드
초록
Recently, many studies are being conducted to extract emotion from text and verify its information power in the field of finance, along with the recent development of big data analysis technology. A number of prior studies use pre-defined sentiment dictionaries or machine learning methods to extract sentiment from the financial documents. However, both methods have the disadvantage of being labor-intensive and subjective because it requires a manual sentiment learning process. In this study, we developed a financial sentiment dictionary that automatically extracts sentiment from the body text of analyst reports by using modified Bayes rule and verified the performance of the model through a binary classification model which predicts actual stock price movements. As a result of the prediction, it was found that the proposed financial dictionary from this research has about 4% better predictive power for actual stock price movements than the representative Loughran and McDonald’s (2011) financial dictionary. The sentiment extraction method proposed in this study enables efficient and objective judgment because it automatically learns the sentiment of words using both the change in target price and the cumulative abnormal returns. In addition, the dictionary can be easily updated by re-calculating conditional probabilities. The results of this study are expected to be readily expandable and applicable not only to analyst reports, but also to financial field texts such as performance reports, IR reports, press articles, and social media.
Abstract
Recently, many studies are being conducted to extract emotion from text and verify its information power in the field of finance, along with the recent development of big data analysis technology. A number of prior studies use pre-defined sentiment dictionaries or machine learning methods to extract sentiment from the financial documents. However, both methods have the disadvantage of being labor-intensive and subjective because it requires a manual sentiment learning process. In this study, we developed a financial sentiment dictionary that automatically extracts sentiment from the body text of analyst reports by using modified Bayes rule and verified the performance of the model through a binary classification model which predicts actual stock price movements. As a result of the prediction, it was found that the proposed financial dictionary from this research has about 4% better predictive power for actual stock price movements than the representative Loughran and McDonald’s (2011) financial dictionary. The sentiment extraction method proposed in this study enables efficient and objective judgment because it automatically learns the sentiment of words using both the change in target price and the cumulative abnormal returns. In addition, the dictionary can be easily updated by re-calculating conditional probabilities. The results of this study are expected to be readily expandable and applicable not only to analyst reports, but also to financial field texts such as performance reports, IR reports, press articles, and social media.
참고문헌 (28)
- Bannier, C., "Content Analysis of Business Communication : Introducing a German Dictionary", Journal of Business Economics, 89(1), pp.79~123 (2019)
- Bollen J., "Twitter Mood Predicts the Stock Market", Journal of Computational Science, 2(1), pp.1~8 (2011)
- S. McKay Price, "Conference Call Tone and Stock Returns: Evidence from the Stock Exchange of Hong Kong", Asia-Pacific Journal of Financial Studies, 46(5), pp.667~685 (2017), 한국증권학회[DOI]
- Buehlmaier, M. M., "Are Financial Constraints Priced? Evidence from Textual Analysis", The Review of Financial Studies, 31(7), pp.2693~2728 (2018)
- Cambria E., "New Avenues in Opinion Mining and Sentiment Analysis", IEEE Intelligent Systems, 28(2), pp.15~21 (2013)
- Chen, H., "Wisdom of Crowds : The Value of Stock Opinions Transmitted Through Social Media", The Review of Financial Studies, 27(5), pp.1367~1403 (2014)
- 조수지, "애널리스트 목표가를 활용한 최적 투자의사결정 방안에 관한 연구", 한국산업경영시스템학회지, 43(4), pp.229~235 (2020), 한국산업경영시스템학회[DOI]
- 양철원, "기업 재무분석을 위한 한국어 감성사전 구축", 한국증권학회지, 50(2), pp.135~170 (2021), 한국증권학회[DOI]
- Conley, C., "Crowdsourcing Content Analysis for Managerial Research", Management Decision, 52(4), pp.675~688 (2014)
- Das S., "Yahoo! for Amazon : Sentiment Extraction from Small Talk on the Web", Management Science, 53(9), pp.1375~1388 (2007)
- Deng, S., "Combining Technical Analysis with Sentiment Analysis for Stock Price Prediction", Dependable, Autonomic and Secure Computing (DASC), 2011 IEEE Ninth International Conference, pp.800~807 (2011)
- Garca, D., "Sentiment During Recessions", The Journal of Finance, 68(3), pp.1267~1300 (2013)
- Guo, H., "Does Prospectus AE Affect IPO Underpricing? A Content Analysis of the Chinese Stock Market", International Review of Economics and Finance, 82, pp.1~12 (2022)
- Heidari M., "Financial Footnote Analysis:Developing a Text Mining Approach", Proceedings of International Conference on Data Mining (DMIN), pp.10~16 (2015)
- Huang, A. H., "Evidence on the Information Content of Text in Analyst Reports", Accounting Review, 89(6), pp.2151~2180 (2014)
- 김홍삼, "빅데이터 분석 기반의 오피니언 마이닝을 이용한 정보화 사업 평가 분석", 한국산업경영시스템학회지, 41(1), pp.1~10 (2018), 한국산업경영시스템학회[DOI]
- 조성욱, "한국어 텍스트 분석과 적용: 머신러닝을 통한 증권발행신고서의 비정형화된 텍스트 분석", 한국증권학회지, 48(2), pp.215~235 (2019), 한국증권학회[DOI]
- 이의섭, "Does Adoption of K-IFRS Increase Upward Bias in Analysts’ Earnings Forecasts?", 재무관리연구, 36(1), pp.179~205 (2019), 한국재무관리학회[DOI]
- Li F., "The Information Content of Forward-Looking Statements in Corporate Filings-A Naïve Bayesian Machine Learning Approach", Journal of Accounting Research, 48(5), pp.1049~1102 (2010)
- Li, F., "A Measure of Competition Based on 10-K Filings", Journal of Accounting Research, 51(2), pp.399~436 (2013)
- Liang D., "The Information Content of Analysts’ Textual Reports and Stock Returns:Evidence from China", Finance Research Letters, 46(Part. B), pp.1~6 (2022)
- Loughran T., "When Is a Liability Not a Liability? Textual Analysis, Dictionaries, and 10-Ks", The Journal of Finance, 66(1), pp.35~65 (2011)
- Schumaker, R. P., "A Quantitative Stock Prediction System Based on Financial News", Information Processing & Management, 45(5), pp.571~583 (2009)
- Shmueli, G., "To Explain or to Predict?", Statistical Science, 25, pp.289~310 (2010)
- Tetlock, P. C., "Giving Content to Investor Sentiment : The Role of Media in the Stock Market", The Journal of Finance, 62(3), pp.1139~1168 (2007)
- Tetlock, P. C., "More Than Words : Quantifying Language to Measure Firms’Fundamentals", The Journal of Finance, 63(3), pp.1437~1467 (2008)
- 양철원, "애널리스트 보고서 제목의 정보력 검증: 텍스트 어조를 중심으로", 재무관리연구, 38(3), pp.1~38 (2021), 한국재무관리학회[DOI]
- 유지돈, "인터넷 뉴스 빅데이터를 활용한 기업 주가지수 예측", 한국산업경영시스템학회지, 41(3), pp.154~161 (2018), 한국산업경영시스템학회[DOI]