<?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">SE</journal-id><journal-title-group><journal-title>Society and Economy</journal-title></journal-title-group><issn>2995-4959</issn><eissn>2995-4975</eissn><publisher><publisher-name>Art and Technology</publisher-name></publisher></journal-meta><article-meta><article-id pub-id-type="doi">10.61369/SE.2026060006</article-id><article-categories><subj-group subj-group-type="heading"><subject>Article</subject></subj-group></article-categories><title>投资者舆情情绪极性对股票收益的中介效应研究—— 基于多模型融合的创新视角</title><url>https://artdesignp.com/journal/SE/4/6/10.61369/SE.2026060006</url><author>陈云</author><pub-date pub-type="publication-year"><year>2026</year></pub-date><volume>4</volume><issue>6</issue><history><date date-type="pub"><published-time>2026-06-20</published-time></date></history><abstract>本研究突破传统单一模型分析框架，创新性地融合Baron-Kenny 中介效应模型、Sobel 检验、Bootstrap 方法、GARCH 族模型、面板向量自回归（PVAR）以及门限回归等多种前沿计量方法，构建了一个多维度、多层次的分析体系，深入探讨投资者舆情情绪极性对股票收益的影响机制与传导路径。研究发现：（1）波动率在舆情情绪与股票收益之间起到了显著的完全中介作用，中介效应占比高达1266.05%，揭示了舆情影响市场的核心传导渠道；（2）通过GARCH、EGARCH 和TGARCH 模型的对比分析，发现舆情情绪对条件波动率存在非对称影响，负面舆情的冲击效应更为显著；（3）面板向量自回归分析表明，舆情情绪、收益率和波动率之间存在复杂的动态交互关系，形成了一个完整的反馈回路；（4）门限回归分析发现，当舆情情绪低于门槛值时，中介效应更为显著。</abstract><keywords>投资者舆情,情绪极性,中介效应,波动率,多模型融合,行为金融</keywords></article-meta></front><body/><back><ref-list><ref id="B1" content-type="article"><label>1</label><element-citation publication-type="journal"><p>[1]Baron, R. M., &amp;amp; Kenny, D. A. (1986). The moderator-mediator variable distinctionin social psychological research: Conceptual, strategic, and statistical considerations.Journal of Personality and Social Psychology, 51(6), 1173-1182.[2]Preacher K J, Leonardelli G J. Calculation for the Sobel test[J]. Retrieved January,2001, 20: 2009.[3]Rajh-Weber H, Huber S E, Arendasy M. Using heteroskedasticity-consistentstandard errors and the bootstrap for linear regression analysis available in SPSS: Atutorial[J]. Advances in Methods and Practices in Psychological Science, 2026, 9(1):25152459251408046.[4]Bollerslev T, Engle R F, Nelson D B. ARCH models[J]. Handbook of econometrics,1994, 4: 2959-3038.[5]Bhat P A A R, Shakila B, Pinto P, et al. Comparing the performance of GARCHfamily models in capturing stock market volatility in India[J]. Journal of Management,2034, 11(3): 11-20.[6]Holtz-Eakin D, Newey W, Rosen H S. Estimating vector autoregressions withpanel data[J]. Econometrica: Journal of the econometric society, 1988: 1371-1395.[7]Wang Y. Asymptotic nonequivalence of GARCH models and diffusions[J]. The Annalsof Statistics, 2002, 30(3): 754-783.[8]Apostolakis G, Papadopoulos A P. Financial stability, monetary stability andgrowth: a PVAR analysis[J]. Open Economies Review, 2019, 30(1): 157-178.[9]Amaro M, Molontay R. From Beijing to Paris: Media representation and sentimentdynamics of the Olympics and Paralympics across traditional and social platforms(2008&amp;ndash;2024)[J]. International Journal of Sports Science &amp;amp; Coaching, 2026:17479541261435444.</p><pub-id pub-id-type="doi"/></element-citation></ref></ref-list></back></article>
