考虑“发布者—关注者”投资者情绪对股市的影响  

Research on the Relationship Between“Poster-followers”BSI and Stock Market

作　　者：庞智亮 张宁 何立峰 景艳锋 PANG Zhi-liang;ZHANG Ning;HE Li-feng;JING Yan-feng(School of Business, Qingdao University, Qingdao 266100, China)

机构地区：[1]青岛大学商学院,青岛266100

出　　处：《青岛大学学报（自然科学版）》2020年第4期93-100,共8页Journal of Qingdao University(Natural Science Edition)

基　　金：国家民委民族研究项目(批准号:2018-GMB-022)资助;山东省社科规划项目(批准号:18CHLJ22)资助。

摘　　要：基于网络爬虫技术与文本挖掘方法构建投资者情绪,综合考虑情绪发布者的影响力与关注者的认同程度,构建了“发布者—关注者”投资者情绪指标PFBSI(Poster-followers BSI)。采用VAR模型验证PFBSI与股票市场的关联性,并建立SVM模型进一步验证PFBSI对股票市场走势的预测作用。研究结果显示,基于股吧文本数据构建的PFBSI投资者情绪指标与股市存在较强的短期关系,相对于其他各类情绪指标,能够提高股票市场走势的预测准确率;改进了现有的BSI指标构造方法,有利于各类投资主体更好做出的决策。Based on web crawler technology and text mining method,the investors sentiment index PFBSI(Poster-followers BSI)is constructed by considering the influence of poster's emotion and the recognition degree of followers.VAR model is used to verify the correlation between PFBSI and stock market,and SVM model is established to further verify the prediction effect of PFBSI on stock market trend.The results show that there is a strong short-term relationship between PFBSI investor sentiment index and stock market based on stock bar text data.Compared with other kinds of sentiment indexes,PFBSI can improve the prediction accuracy of stock market trend.This study improves the existing BSI index construction method,which is conducive to better decision-making of various investors.

关 键 词：股票评论 股评关注度 文本挖掘 投资者情绪 

分 类 号：G315[文化科学] G358