뉴스 감성 분석을 이용한 딥러닝 기반 주가 예측에 대한 연구
A study on Deep Learning-based Stock Price Prediction using News Sentiment Analysis
2
조회
0
다운로드
7
인용
0
참고문헌
키워드
초록
주가는 거래량, 종가 등과 같은 숫자 기반의 내부적인 요인뿐만 아니라 법, 유행 등 여러 외부요인에 의해 영향을 받는다. 수많은 요인이 주가에 영향을 미치기 때문에 단편적인 주식 데이터만을 이용한 정확한 주가 예측은 매우 어려운 일이다. 특히 기업의 가치는 실제 주식을 거래하는사람들의 인식에 영향을 많이 받기 때문에 특정 기업에 대한 감성 정보가 중요한 요인으로 여겨진다. 본 논문에서는 시간적 특성을 고려한 뉴스 데이터의 감성 분석을 이용한 딥러닝 기반 주가예측 모델을 제안하고자 한다. 주식과 뉴스 데이터, 서로 다른 특성을 가진 2개의 이종 데이터를시간 크기에 따라 통합하여 모델의 입력으로 사용하며, 시간 크기와 감성 지표가 주가 예측에 미치는 영향에 대해 최종적으로 비교 및 분석한다. 또한 우리는 기존 모델과의 비교 실험을 통해제안 모델의 정확성이 개선되었음을 검증한다.
Abstract
Stock prices are influenced by a number of external factors, such as laws and trends, as well as number-based internal factors such as trading volume and closing prices. Since many factors affect stock prices, it is very difficult to accurately predict stock prices using only fragmentary stock data. In particular, since the value of a company is greatly affected by the perception of people who actually trade stocks, emotional information about a specific company is considered an important factor. In this paper, we propose a deep learning-based stock price prediction model using sentiment analysis with news data considering temporal characteristics. Stock and news data, two heterogeneous data with different characteristics, are integrated according to time scale and used as input to the model, and the effect of time scale and sentiment index on stock price prediction is finally compared and analyzed. Also, we verify that the accuracy of the proposed model is improved through comparative experiments with existing models.
참고문헌 (21)
- B. G. Malkiel, "The New Palgrave:Finance", pp.127~134 (1989), Norton
- S. Mohan, "Stock Price Prediction Using News Sentiment Analysis", 2019 IEEE Fifth International Conference on Big Data Computing Service and Applications (BigDataService), pp.205~208 (2019)
- Gite S, "Explainable stock prices prediction from financial news articles using sentiment analysis", PeerJ Computer Science, 7, pp.e340~ (2021)
- X. Li, "Does summarization help stock prediction? a news impact analysis", IEEE Intelligent Systems, 30(3), pp.26~34 (2015)
- D. Duong, "Stock market prediction using financial news articles on ho chi minh stock exchange", Proceedings of the 10th International Conference on Ubiquitous Information Management and Communication ser. IMCOM ‘16, pp.71:1~71:6 (2016)
- Y. Wang, "A study of feature construction for text-based forecasting of time series variables", Proceedings of the 2017 ACM on Conference on Information and Knowledge Management ser. CIKM ‘17, pp.2347~2350 (2017)
- Economic Prediction Using Neural Networks: The Case of IBM Daily Stock Returns, ser. Discussion paper-, "H. White", Department of Economics University of California San Diego. Department of Economics, University of California, ~ (1988)
- E. Hoseinzade, "CNNpred: CNN-based stock market prediction using a diverse set of variables", Expert Systems with Applications, 129, pp.273~285 (2019)
- Guo, Baicun, "Research on Stock Price Forecast based on Resnet and LSTM", Frontiers in Economics and Management, 3(5), pp.161~167 (2022)
- K. A. Althelaya, "Evaluation of Bidirectional LSTM for Short and Long-Term Stock Market Prediction", Proc. of the 9th International Conference on Information and Communication Systems, pp.151~156 (2018)
- Yao, Yifan, "Combination of window-sliding and prediction range method based on LSTM model for predicting cryptocurrency", ~ (2021)
- Schumaker, Robert P, "Textual analysis of stock market prediction using breaking financial news: The AZFin text system", ACM Transactions on Information Systems, 27(2), pp.1~19 (2009)
- Tetlock, Paul C, "More than words: Quantifying language to measure firms'fundamentals", The journal of finance, 63(3), pp.1437~1467 (2008)
- Li, Xiaodong, "Does summarization help stock prediction? A news impact analysis", IEEE intelligent systems, 30(3), pp.26~34 (2015)
- "Google Finance"[URL]
- N. V. Chawla, "Editorial: Special issue on learning from imbalanced data sets", ACM SIGKDD Explor. Newslett, 6(1), pp.1~6 (2004)
- "KoreanNewsCrawler Open source"[URL]
- "Naver Finance News"[URL]
- "Yahoo Finance"[URL]
- "Pororo"[URL]
- 김승우, "시장을 이길 수 있는가?―20세기 주식시장 읽기와 투자 기법들의 역사", 역사비평, (138), pp.8~35 (2022), 역사문제연구소