Open Access

ARTICLE

Structured Multi-Head Attention Stock Index Prediction Method Based Adaptive Public Opinion Sentiment Vector

Cheng Zhao¹, Zhe Peng², Xuefeng Lan³, Yuefeng Cen⁴, Zuxin Wang^5,*

1 School of Economics, Zhejiang University of Technology, Hangzhou, China
2 College of Management, Zhejiang University of Technology, Hangzhou, China
3 Informatization Office, Zhejiang University of Technology, Hangzhou, China
4 School of Information and Electronic Engineering, Zhejiang University of Science & Technology,Hangzhou, China
5 School of Economics and Management, Universiti Putra Malaysia, Daerah Petaling, Negeri Selangor, Malaysia

* Corresponding Author: Zuxin Wang. Email:

Computers, Materials & Continua 2024, 78(1), 1503-1523. https://doi.org/10.32604/cmc.2024.039232

Received 16 January 2023; Accepted 07 April 2023; Issue published 30 January 2024

Abstract

The present study examines the impact of short-term public opinion sentiment on the secondary market, with a focus on the potential for such sentiment to cause dramatic stock price fluctuations and increase investment risk. The quantification of investment sentiment indicators and the persistent analysis of their impact has been a complex and significant area of research. In this paper, a structured multi-head attention stock index prediction method based adaptive public opinion sentiment vector is proposed. The proposed method utilizes an innovative approach to transform numerous investor comments on social platforms over time into public opinion sentiment vectors expressing complex sentiments. It then analyzes the continuous impact of these vectors on the market through the use of aggregating techniques and public opinion data via a structured multi-head attention mechanism. The experimental results demonstrate that the public opinion sentiment vector can provide more comprehensive feedback on market sentiment than traditional sentiment polarity analysis. Furthermore, the multi-head attention mechanism is shown to improve prediction accuracy through attention convergence on each type of input information separately. The mean absolute percentage error (MAPE) of the proposed method is 0.463%, a reduction of 0.294% compared to the benchmark attention algorithm. Additionally, the market backtesting results indicate that the return was 24.560%, an improvement of 8.202% compared to the benchmark algorithm. These results suggest that the market trading strategy based on this method has the potential to improve trading profits.

---

Keywords

---