金融评论文本情感分析研究趋势与未来展望  

Trends and Future Prospects in Sentiment Analysis of Financial Reviews Texts

作　　者：吴江[1] 段一奇 Wu Jiang;Duan Yiqi(School of Information Management,Wuhan University,Wuhan,430072;AVIC Securities Co.,Ltd,Shenzhen,518057)

机构地区：[1]武汉大学信息管理学院,武汉430072 [2]中航证券有限公司,深圳518057

出　　处：《信息资源管理学报》2025年第1期86-101,共16页Journal of Information Resources Management

基　　金：教育部哲学社会科学研究重大课题攻关项目“网络环境下大数据新动能机制研究”(20JZD024);国家自然科学基金重点项目“网络视角下乡村产业互联网的数智赋能研究”(72232006)的研究成果之一。

摘　　要：以近年来国内外金融评论文本情感分析相关工作为研究对象,总结梳理该领域的发展脉络,从技术驱动和内容驱动双重视角对该领域研究趋势进行分析。在技术驱动方面,概括了从词典、传统机器学习到深度学习的情感分析技术发展历程;在内容驱动方面,利用BERTopic及LLaMA3对文献观点文档进行主题聚类,并通过动态主题建模分析领域发展趋势。研究发现,国内研究趋势由金融情感分析方法研究转向情绪影响市场预测相关研究,国外则持续深化深度学习应用,并预示着金融文本情感分析建模在未来更可能引起关注。最后,结合两方面的分析,从高质量数据集构建、金融评论细粒度情感分析以及情感分析效果的可解释性进行研究展望,为该领域相关研究提供参考和思路借鉴。This study surveys recent advancements in sentiment analysis of financial review texts,both domestically and internationally,to delineate the field’s developmental trajectory.Adopting dual perspectives of technology-driven and content-driven approaches,it scrutinizes prevailing research trends.Technologically,the evolution from lexicon-based methods,through traditional machine learning,to deep learning paradigms is summarized.Content-wise,BERTopic and LLaMA3 are employed for document clustering based on scholarly viewpoints,with dynamic topic modeling elucidating domain progress.Findings indicate a domestic transition from sentiment analysis methods to investigations of emotional impacts on financial market prediction.Meanwhile,international research continues progressing deep learning applications while revealing emerging interests in financial sentiment modeling.By integrating these observations,the paper proposes future directions including:(1)constructing high-quality datasets,(2)conducting granular sentiment analysis of financial discourse,and(3)improving the interpretability of analytical outcomes.These recommendations aim to establish methodological foundations for subsequent studies in this field.

关 键 词：金融评论 情感分析 研究趋势 BERTopic LLaMA3 

分 类 号：G353[文化科学—情报学]