Using a semisupervised topic model on 7 million New York Times articles spanning 160 years, we test whether topics of media discourse predict future stock market excess returns to test rational and behavioral hypotheses about market valuation of disaster risk. Media discourse data address the challenge of sample size even when disasters are rare. Our methodology avoids look-ahead bias and addresses semantic shifts. Our discourse topics positively predicts market excess returns, with War having an out-of-sample R 2 of 1.35%. We call this effect the war return premium. The war return premium has increased in more recent time periods. (JEL G10, G11, G12, G14, G17, G41, N00)

中文翻译：

---

战争话语和灾难溢价：来自股市的 160 年证据


使用跨越 160 年的 700 万篇《纽约时报》文章的半监督主题模型，我们测试了媒体话语主题是否预测了未来的股市超额回报，以测试关于灾害风险市场估值的理性和行为假设。媒体话语数据解决了样本量的挑战，即使在灾难很少见的情况下也是如此。我们的方法避免了前瞻性偏差并解决了语义变化。我们的论述主题积极预测市场超额回报，战争的样本外 R 2 为 1.35%。我们将这种效应称为战争回报溢价。战争回报保费在最近的一段时间内有所增加。（JEL G10、G11、G12、G14、G17、G41、N00）