本文在Loughran and MacDonald(2011)词典的基础上通过人工筛选和word2vec算法扩充,构建了一个更新更全面的中文金融情感词典。我们使用该情感词典计算我国财经媒体文本情绪指标,发现媒体文本情绪可以更准确地衡量我国股市投资者情绪的...本文在Loughran and MacDonald(2011)词典的基础上通过人工筛选和word2vec算法扩充,构建了一个更新更全面的中文金融情感词典。我们使用该情感词典计算我国财经媒体文本情绪指标,发现媒体文本情绪可以更准确地衡量我国股市投资者情绪的变化,对我国股票回报有显著的样本内和样本外预测能力。媒体文本情绪对一些重要的宏观经济指标也有显著的预测能力,具有重要的学术和实践应用价值。展开更多
This paper presents a comprehensive study on predicting the cross section of Chinese stock market returns with a large panel of 75 individual firm characteristics.We use not only the traditional Fama-MacBeth regressio...This paper presents a comprehensive study on predicting the cross section of Chinese stock market returns with a large panel of 75 individual firm characteristics.We use not only the traditional Fama-MacBeth regression,but also the"big-data"econometric methods:principal component analysis(PCA),partial least squares(PLS),and forecast combination to extract information from all the 75 firm characteristics.These characteristics are important return predictors,with statistical and economic significance.Furthermore,firm characteristics that are related to trading frictions,momentum,and profitability are the most effective predictors of future stock returns in the Chinese stock market.展开更多
文摘本文在Loughran and MacDonald(2011)词典的基础上通过人工筛选和word2vec算法扩充,构建了一个更新更全面的中文金融情感词典。我们使用该情感词典计算我国财经媒体文本情绪指标,发现媒体文本情绪可以更准确地衡量我国股市投资者情绪的变化,对我国股票回报有显著的样本内和样本外预测能力。媒体文本情绪对一些重要的宏观经济指标也有显著的预测能力,具有重要的学术和实践应用价值。
基金We are grateful to seminar participants at Beijing University,Central University of Finance and Economics,Georgia State University,Hunan University,Indiana University,Renmin University,Shanghai University of Finance and Economics,Washington University in St.Louis,and conference partidpants at the 20(71872195,71602198)Beijing Natural Science Foundation(9174045)+1 种基金Hunan Natural Science Foundation(2019JJ50058)the Fundamental Research Funds for the Central Universities.
文摘This paper presents a comprehensive study on predicting the cross section of Chinese stock market returns with a large panel of 75 individual firm characteristics.We use not only the traditional Fama-MacBeth regression,but also the"big-data"econometric methods:principal component analysis(PCA),partial least squares(PLS),and forecast combination to extract information from all the 75 firm characteristics.These characteristics are important return predictors,with statistical and economic significance.Furthermore,firm characteristics that are related to trading frictions,momentum,and profitability are the most effective predictors of future stock returns in the Chinese stock market.
