The Handbook of News Analytics in Finance

5.3 INDUSTRY-LEVEL SENTIMENT

In the previous section, I demonstrated how to construct a market-level news sentiment index that can be used to predict the future direction of the S&P 500. Here, I will focus on constructing market-neutral strategies taking long and short positions in the top- and bottom-ranked industries, respectively. Being able to successfully rank industries based on sentiment should enhance the performance of a strategy, since more targeted investments can be made towards expected outperformers and underperformers during periods with long and short exposures, respectively.

Table 5.1. Performance statistics covering the out-of-sample period May 2005 through December 2009 for the strategies based on the Market-Level Sentiment Index (column 3) with an Event Novelty Score filter (ENS = 100), the Market-Level Sentiment Index (column 4) without an Event Novelty Score filter, and the 1-month price momentum strategy based on the S&P 500 (column 5). Pre-October and Post-October refer to the market high in October 2007

Table 5.2. Yearly annualized return covering the out-of-sample period May 2005 through December 2009 for strategies based on the Market-Level Sentiment Index (column 2) with an Event Novelty Score filter (ENS=100), the Market-Level Sentiment Index (column 3) without an Event Novelty Score filter, and the 1-month price momentum strategy based on the S&P 500 ...