<?xml version="1.1" encoding="utf-8"?>
<article xsi:noNamespaceSchemaLocation="http://jats.nlm.nih.gov/publishing/1.1/xsd/JATS-journalpublishing1-mathml3.xsd" dtd-version="1.1" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"><front><journal-meta><journal-id journal-id-type="publisher-id">ER</journal-id><journal-title-group><journal-title>Economics Research</journal-title></journal-title-group><issn>2997-058X</issn><eissn>2997-0598</eissn><publisher><publisher-name>Art and Technology</publisher-name></publisher></journal-meta><article-meta><article-id pub-id-type="doi">10.61369/ER.2025060012</article-id><article-categories><subj-group subj-group-type="heading"><subject>Article</subject></subj-group></article-categories><title>投资者舆情与上市公司股价财务关联研究
—— 基于DeepSeek大模型情感分析</title><url>https://artdesignp.com/journal/ER/2/6/10.61369/ER.2025060012</url><author>陈云</author><pub-date pub-type="publication-year"><year>2025</year></pub-date><volume>2</volume><issue>6</issue><history><date date-type="pub"><published-time>2025-06-20</published-time></date></history><abstract>本研究构建了一个基于轻量级大语言模型（DeepSeek）的细粒度舆情量化框架，对东方股吧中文评论进行连续型情感评分与关联度过滤，生成日度加权情绪指数。基于2024年10只A股日频数据，结合计量与机器学习方法检验情绪对股价的非线性影响及时效特征。结果表明，社交媒体情绪与股价变动呈显著非线性关联，影响集中于短期（领先1-3天），中长期预测性能下降但存在动态波动；个股情绪敏感性存在异质性，科技类及高关注公司反应更敏感。本研究在方法上实现了基于大模型的细粒度情绪量化，在视角上融合市场反应与时间效应，揭示了情绪与股价间的非线性短周期机制，为后续融合多源数据探索情绪传导路径提供基础。</abstract><keywords>投资者情绪,股票财务指标预测,大语言模型,机器学习</keywords></article-meta></front><body/><back><ref-list><ref id="B1" content-type="article"><label>1</label><element-citation publication-type="journal"><p>[1] 陈其安, 朱敏, 赖琴云. 基于投资者情绪的投资组合模型研究[J].中国管理科学,2012,20(3):47-56.[2] 王春. 投资者情绪对股票市场收益和波动的影响-基于开放式股票型基金资金净流入的实证研究[J].中国管理科学,2014,22(9):49-56.[3] 于孝建, 刘国鹏, 刘建林, 等. 基于LSTM网络和文本情感分析的股票指数预测[J].中国管理科学,2024,32(8):25-35.[4]Liu,Q.,Lee,W.S.,Huang,M.,&amp;amp;Wu,Q.(2023).Synergy between stock prices and investor sentiment in social media.Borsa Istanbul Review,23(1),76-92.[5]Malkiel,B.G.(1989).Efficient market hypothesis.In Finance(pp.127-134).Palgrave Macmillan,London.[6]McGurk,Z.,Nowak,A.,&amp;amp;Hall,J.C.(2020).Stock returns and investor sentiment:textual analysis and social media.Journal of Economics and Finance,44(3),458-485.[7]Obaid,K.,&amp;amp;Pukthuanthong,K.(2022).A picture is worth a thousand words:Measuring investor sentiment by combining machine learning and photos from news.Journal of Financial Economics,144(1),273-297.[8]Simon,H.A.(1990).Bounded rationality.In Utility and probability(pp.15-18).Palgrave Macmillan,London.[9]Sun,Y.,Zeng,X.,Zhou,S.,Zhao,H.,Thomas,P.,&amp;amp;Sun,L.(2021).What investors say is what the market says:Measuring China&amp;rsquo;s real investor sentiment.Personal and Ubiquitous Computing,25(3),587-599.[10]Xie,D.,Cui,Y.,&amp;amp;Liu,Y.(2023).How does investor sentiment impact stock volatility?New evidence from Shanghai A-shares market.China Finance Review International,13(1),102-120.[11]Xie,X.,Yang,X.,&amp;amp;Cui,R.(2025,March).Research on Investor Education in China Based on Large Language Models.In 2025 14th International Conference on Educational and Information Technology(ICEIT)(pp.484-489).IEEE.[12]Yu,Y.,Zhou,R.,Jiang,R.,&amp;amp;Liu,F.(2025).Exploring the role of social bots in cryptocurrency manipulation:Machine learning insights from the LUNA crash.Electronic Markets,35(1),110.[13]Zheng,B.(2022).Investor Sentiment,Five ‐factor Model and Portfolio Returns:Empirical Research on China&amp;rsquo;s A ‐Share Markets.World Scientific Research Journal,8(3),485-500.</p><pub-id pub-id-type="doi"/></element-citation></ref></ref-list></back></article>
