arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2504.02429cs.CE
收藏

MulFSA: 用于债券市场的多级财务情绪分析框架

MulFSA: Multi-level Financial Sentiment Analysis Framework for Bond Market

Sichuan University(四川大学);National University of Singapore(新加坡国立大学);Fudan University(复旦大学)

Yiwei Liu, Junbo Wang, Lei Long, Xin Li, Ruiting Ma, Yuankai Wu, Xuebin Chen

AI总结:

本文提出MulFSA框架,基于预训练语言模型和大语言模型,系统整合企业级微观情绪、行业级中观情绪和持续时间感知平滑,以建模文本影响的延迟和持续性,从而提升信用利差预测的准确性。

摘要:

现有的金融情绪分析方法由于其单层方法和对时间动态的忽视,往往无法捕捉债券市场中风险的多面性。我们提出基于预训练语言模型(PLMs)和大语言模型(LLMs)的多级金融情绪分析(MulFSA)框架,该框架系统整合企业特定的微观情绪、行业特定的中观情绪以及持续时间感知的平滑处理,以建模文本影响的延迟和持续性。将MulFSA应用于我们构建的全面的中国债券市场语料库(2013-2023,135万文本),我们提取出一个每日综合情绪指数。实证结果表明,当将情绪纳入信用利差预测时,MAE和MAPE分别减少了10.25%和11.94%,情绪变化与主要社会风险事件和企业特定危机密切相关。项目页面:https://mulfsa.github.io/.

英文摘要:

Existing financial sentiment analysis methods often fail to capture the multi-faceted nature of risk in bond markets due to their single-level approach and neglect of temporal dynamics. We propose Multi-level Financial Sentiment Analysis (MulFSA) based on pre-trained language models (PLMs) and large language models (LLMs), a novel framework that systematically integrates firm-specific micro-level sentiment, industry-specific meso-level sentiment, and duration-aware smoothing to model the latency and persistence of textual impact. Applying MulFSA to the comprehensive Chinese bond market corpus constructed by us (2013-2023, 1.35M texts), we extracted a daily composite sentiment index. Empirical results show statistically measurable improvements in credit spread forecasting when incorporating sentiment (10.25% MAE and 11.94% MAPE reduction), with sentiment shifts closely correlating with major social risk events and firm-specific crises. Project Page: https://mulfsa.github.io/.

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。

↑