主题：The Colour of Finance Words

主讲人：南卫理公会大学考克斯商学院 胡晓雯助理教授

主持人：工商管理学院 赵琳教授

时间：2023年3月28日（周二）9:00—10:00

直播平台及会议ID：腾讯会议 ID： 476-976-571

主办单位：工商管理学院 科研处

主讲人简介：

Dr. Hu is an Assistant Professor of Finance at the Cox School of Business, Southern Methodist University. She received her Ph.D. in Finance from the Leeds School of Business at the University of Colorado at Boulder in 2022. Prior to that, she obtained a Ph.D. in Statistics from Southern Methodist University.Dr. Hu's research focuses on empirical asset pricing, financial narratives, news media, behavioral finance, FinTech, mutual funds, household finance, textual analysis, and machine learning. Her work has been published in Journal of Financial Economics and has received The Best FinTech Paper Award at the 2020 Toronto FinTech Conference and has been featured in Wall Street Portal. As a passionate teacher, Dr. Hu has taught various courses in finance and statistics and has received multiple teaching awards.

胡晓雯，南卫理公会大学考克斯商学院金融学助理教授，科罗拉多大学金融学博士和南卫理公会大学统计学博士，主要从事实证资产定价、新闻媒体、行为金融学、金融科技、共同基金、家庭金融、文本分析和机器学习领域的研究。她的研究成果已发表在《Journal of Financial Economics》上，并获得 2020 年多伦多金融科技大会最佳金融科技论文奖。她热爱教学，有着丰富的金融和统计相关课程教学经验，并获得了多项教学奖项。

内容简介：

Our paper relies on stock price reactions to color words, in order to provide new dictionaries of positive and negative words in a finance context. We extend the machine learning algorithm of Taddy (2013), adding a cross-validation layer to avoid over-fitting. In head-to-head comparisons, our dictionaries outperform the standard bag-of-words approach (Loughran and McDonald, 2011) when predicting stock price movements out-of-sample. By comparing their composition, word-by-word, our method refines and expands the sentiment dictionaries in the literature. The breadth of our dictionaries and their ability to disambiguate words using bigrams both help to color finance discourse better.

《金融词汇的色彩》是一篇由Diego Garcia、Xiaowen Hu和Maximilian Rohrer共同撰写的研究论文，发表在Journal of Financial Economics（JFE）2023年三月。该论文提出了一种新的方法来分析金融话语中的情绪色彩，通过分析股票价格对情绪词汇的反应来构建正负面情感词典。这种方法不同于传统的词袋模型，而是利用机器学习算法对大量文本进行训练，以获取更准确、更全面的情感信息。在研究中，作者使用了大量的数据集和实证分析，证明了所提出的方法在预测股票价格变动时表现更好。此外，作者还通过逐字比较词典的组成来完善和扩展了文献中的情感词典。文章还探讨了情感得分分布、单个颜色词汇对情感得分的影响等问题，并提供了开源代码和数据以供读者参考。该研究为金融领域情感分析提供了新思路和方法，并具有相当的实际应用价值。例如，在股票市场上，投资者可以利用这种方法来预测股票价格变动趋势，并做出相应决策。此外，在金融舆情监测方面也有广泛应用前景，为我们理解金融话语中隐藏着怎样的情感信息提供了新思路和方法。