Construction of Financial News Sentiment Indices Using Deep Neural Networks

13 Pages Posted: 8 Nov 2019

See all articles by Shaokai Wang

Shaokai Wang

Peking University - Guanghua School of Management; Harvest Fund Management Co., Ltd.

Zili Zhang

Harvest Fund Management Co., Ltd.

Date Written: June 1, 2019

Abstract

With the progress in natural language processing and machine learning, using deep learning techniques to extract valuable information from financial texts has gained popularity among researchers. However, as deep learning models require large amounts of labelled data, current models for financial text mining are sensitive to noise and prone to overfitting due to the lack of labelled data in financial fields. We address this issue by using pretrained word representations and BERT model to leverage knowledge acquired from huge text corpus. In particular, we design a deep neural network model that combines CNN, Att-BLSTM and BERT for predicting financial news sentiment polarity. Then, the news sentiment indices are constructed based on the predictive model. In terms of predicting news sentiment polarity, we show that our model outperforms state-of-the-art competitors. Furthermore, we show that the news sentiment exhibits a significant relationship with stock market returns.

Keywords: News sentiment;Textual tone; Natural language processing; Deep learning

Suggested Citation

Wang, Shaokai and Zhang, Zili, Construction of Financial News Sentiment Indices Using Deep Neural Networks (June 1, 2019). Available at SSRN: https://ssrn.com/abstract=3477690 or http://dx.doi.org/10.2139/ssrn.3477690

Shaokai Wang (Contact Author)

Peking University - Guanghua School of Management ( email )

Peking University
Beijing, Beijing 100871
China

Harvest Fund Management Co., Ltd. ( email )

Beijing
China

Zili Zhang

Harvest Fund Management Co., Ltd.

Beijing
China

Here is the Coronavirus
related research on SSRN

Paper statistics

Downloads
58
Abstract Views
231
rank
376,232
PlumX Metrics