We construct various measures of firm-level climate risk exposure by utilizing natural language processing techniques on firms’ quarterly earnings conference call transcripts. The unsupervised learning method automatically generates five topics aligned with popular climate change concerns. Investors reward firms’ efforts to fight against global warming and transition to a low-carbon economy by developing emission reduction technology and renewable investment. Such firms are less sensitive to the frontier green technology shock and less likely to be subject to penalties related to environmental issues. Therefore they have a lower cost of financing and expected return.

We conduct an empirical analysis on the topic that puts high weight on words about natural disasters. This disaster expos...[ Read more ]

We construct various measures of firm-level climate risk exposure by utilizing natural language processing techniques on firms’ quarterly earnings conference call transcripts. The unsupervised learning method automatically generates five topics aligned with popular climate change concerns. Investors reward firms’ efforts to fight against global warming and transition to a low-carbon economy by developing emission reduction technology and renewable investment. Such firms are less sensitive to the frontier green technology shock and less likely to be subject to penalties related to environmental issues. Therefore they have a lower cost of financing and expected return.

We conduct an empirical analysis on the topic that puts high weight on words about natural disasters. This disaster exposure measure has a significant negative association with firms’ sales growth and profitability. Moreover, firms with higher disaster exposure tend to earn higher expected stock returns than their counterparts with lower exposure, suggesting that firms’ disaster risk exposure significantly affects the cost of equity and market valuations. A long-short portfolio based on this exposure measure generates a positive return of 5% per annum, which cannot be explained by common risk factors and other firm characteristics.

Keywords: Climate change, natural language processing, earnings conference calls, physical risks, transition risks, disaster, cross-section of stock returns.