The Prediction Method of Stock Index Based on Sentiment Analysis of Investors' Comments

Jiaming Zhao, Ke Wen

2022

Abstract

The research content of this paper is to obtain the sentiment of retail investors through text analysis of their comments, and apply it into stock price prediction. In this paper, a retail investor sentiment analysis model Fin-Bert-TextCNN is proposed to construct the sentiment index, exploring the relationship between retail investor sentiment and the stock market, and predict the rise and fall of A shares. This paper finds that Fin-Bert-TextCNN model has higher prediction accuracy and is more suitable for the analysis of financial commentary texts. The deep learning technology used in this paper can well depict the nonlinear relationship between investor sentiment and stock index, which is helpful to prevent and resolve major financial risks.

Paper Citation

in Harvard Style

Zhao J. and Wen K. (2022). The Prediction Method of Stock Index Based on Sentiment Analysis of Investors' Comments. In Proceedings of the 4th International Conference on Economic Management and Model Engineering - Volume 1: ICEMME; ISBN 978-989-758-636-1, SciTePress, pages 478-483. DOI: 10.5220/0012035200003620

in Bibtex Style

@conference{icemme22,
author={Jiaming Zhao and Ke Wen},
title={The Prediction Method of Stock Index Based on Sentiment Analysis of Investors' Comments},
booktitle={Proceedings of the 4th International Conference on Economic Management and Model Engineering - Volume 1: ICEMME},
year={2022},
pages={478-483},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012035200003620},
isbn={978-989-758-636-1},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 4th International Conference on Economic Management and Model Engineering - Volume 1: ICEMME
TI - The Prediction Method of Stock Index Based on Sentiment Analysis of Investors' Comments
SN - 978-989-758-636-1
AU - Zhao J.
AU - Wen K.
PY - 2022
SP - 478
EP - 483
DO - 10.5220/0012035200003620
PB - SciTePress