A BERT-Based Vector Autoregressive Network for Sentiment Analysis of Financial News

被引：0
|
作者：
Zhang D. [1 ]
Wang J. [1 ]
Li Z. [1 ]
Liu R. [2 ]
Zheng W. [1 ,3 ]
机构：
[1] College of Data Science, Taiyuan University of Technology, Taiyuan
[2] Guangdong Province Corps General Staff Department, The Chinese Armed Police Force, Guangzhou
[3] Center for Healthy Big Data, Changzhi Medical College, Shanxi, Changzhi
来源：
Dianzi Keji Daxue Xuebao/Journal of the University of Electronic Science and Technology of China | 2023年 / 52卷 / 02期
关键词：
deep learning; financial news; natural language based financial forecasting; sentiment analysis; time-series analysis;
D O I：
10.12178/1001-0548.2022058
中图分类号：
学科分类号：
摘要：
Stock market forecasting is a difficult problem in the field of financial analysis. The intrinsic information contained in financial news has a great impact on the stock market performance. In this paper, we propose a BERT-based vector autoregressive network (BVANet), which quantifies financial news sentiment by BERT and then combines it with market performance to construct a financial time series vector autoregressive (VAR) model to achieve stock prediction eventually. The results show that BVANet has improved results in extracting news sentiment information and model prediction compared with traditional algorithms, and the sentiment of news has predictive effect on market performance. This study can provide a practical reference for the application of natural language processing in financial prediction. © 2023 Univ. of Electronic Science and Technology of China. All rights reserved.
引用
收藏
页码：263 / 270
页数：7
相关论文
共 22 条
  • [1] FAMA E F., The behavior of stock-market prices, (1965)
  • [2] BENGIO Y, DUCHARME R, VINCENT P., A neural probabilistic language model
  • [3] MIKOLOV T, CHEN K, CORRADO G, Et al., Efficient estimation of word representations in vector space
  • [4] VASWANI A, SHAZEER N, PARMAR N, Et al., Attention is all you need
  • [5] DEVLIN J, CHANG M W, LEE K, Et al., Bert: Pre-Training of deep bidirectional transformers for language understanding
  • [6] GU W T, WANG R, ZHENG S H, Et al., Research on the prediction model of the direction of financial market returns: Based on text big data method, Statistical Research, 37, 11, pp. 68-79, (2020)
  • [7] MENG Z Q, ZHENG G J, ZHAO Y W., The Research on the relationship between network investor emotion and stock market price: Empirical analysis based on text mining technology, Price Theory & Practice, 8, pp. 127-130, (2018)
  • [8] YAO J Q, FENG X, WANG Z J, Et al., Tone, sentiment and market impacts: The construction of Chinese sentiment dictionary in finance, Journal of Management Sciences in China, 24, 5, pp. 26-46, (2021)
  • [9] RAN Y F, JIANG H X., Stock prices prediction based on back propagation neural network and support vector regression, Journal of Shanxi University A (Natural Science Edition), 41, 1, pp. 1-14, (2018)
  • [10] GIDOFALVI G, ELKAN C., Using news articles to predict stock price movements
123