Quantifying Animal Spirits: News Media and Sentiment in the Housing Market

Abstract

This paper develops first measures of housing sentiment for 34 cities across the U.S. by quantifying the qualitative tone of local housing news. I find that housing media sentiment has significant predictive power for future house prices, above and beyond his- torically predictive factors and past returns. Sentiment leads price movements by more than two years, and is highly correlated with available survey expectations measures. The structure of the media sentiment index itself reflects a backward-looking nature consistent with extrapolative expectations. Consistent with theories of sentiment, the media sentiment index has a greater effect in markets with more minority homebuyers, more speculative investors, and across lower-priced homes. Including additional controls for subprime lending and easy credit has no impact on the magnitude of the results, but the predictive effect of sentiment is amplified in markets where more subprime loans were issued. Directly investigating the content across news articles finds that results are not driven by news stories of unobserved fundamentals.

Keywords: Housing Sentiment, Textual Analysis, Housing Bubble, Irrational Exuberance

JEL Classification: G02, R20, G12