arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2306.02136q-fin.STcs.AIcs.CE
收藏

使用FinBERT进行金融情感分析及其在股票走势预测中的应用

Financial sentiment analysis using FinBERT with application in predicting stock movement

University of Rochester(罗切斯特大学)

Tingsong Jiang, Qingyun Zeng

AI总结:

本研究利用FinBERT情感分析与LSTM网络构建深度学习模型,通过对比标准BERT、LSTM和ARIMA,证明情感分析显著提升股市走势预测准确性,并提出优化技术以增强模型性能。

摘要:

在本研究中,我们通过利用FinBERT(一种针对金融文本微调的BERT模型)将情感分析整合到金融框架中,构建了一个基于长短期记忆(LSTM)网络的先进深度学习模型。我们的目标是更准确地预测金融市场趋势。为了评估我们模型的预测能力,我们将其应用于一个全面的股市新闻数据集,并与标准BERT、独立LSTM以及传统ARIMA模型进行了对比分析。我们的研究结果表明,融入情感分析显著增强了模型预测市场波动的能力。此外,我们提出了一套旨在优化模型性能的优化技术,为人工智能驱动的金融领域开发更稳健、更可靠的市场预测工具铺平了道路。

英文摘要:

In this study, we integrate sentiment analysis within a financial framework by leveraging FinBERT, a fine-tuned BERT model specialized for financial text, to construct an advanced deep learning model based on Long Short-Term Memory (LSTM) networks. Our objective is to forecast financial market trends with greater accuracy. To evaluate our model's predictive capabilities, we apply it to a comprehensive dataset of stock market news and perform a comparative analysis against standard BERT, standalone LSTM, and the traditional ARIMA models. Our findings indicate that incorporating sentiment analysis significantly enhances the model's ability to anticipate market fluctuations. Furthermore, we propose a suite of optimization techniques aimed at refining the model's performance, paving the way for more robust and reliable market prediction tools in the field of AI-driven finance.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑