Some good weekend reading here from UNC:
This paper studies the effect of sentiment on asset prices during the first half of the 20th century (1905-1958). As a proxy for sentiment, we use the fraction of positive and negative words in two columns of financial news from the New York Times. The main finding of the paper is that, controlling for other well-known time-series patterns, news content helps predict stock returns at the daily frequency, but only during recessions. A one standard deviation shock to our news measure during recessions changes the conditional average return on the DJIA by eleven basis points over one day.