In “Which News Moves Stock Prices? A Textual Analysis,” Jacob Boudoukh, Ronen Feldman, Shimon Kogan, and Matthew Richardson maintain that common business news sources, such as The Wall Street Journal and the Dow Jones News Service, contain many stories that are not relevant in terms of company fundamentals. They conclude that what is important for stock prices is the type and tone of the news. By applying advanced textual analysis to the actual language of news articles, they discern a strong relationship between information and stock price changes.

Boudoukh and his co-authors combine a dictionary-based sentiment measure, an analysis of phrase-level patterns, and a methodology for identifying relevant events for companies (broken down into 14 categories and 56 subcategories). Over the sample period of 2000-2009 for all S&P 500 companies, the Dow Jones Newswire produced over 1.9 million stories, but the researchers identify only about half of them as relevant events. This breakdown into “identified” and “unidentified” news makes a difference to the analysis, as does using a more sophisticated textual analysis, rather than a simple count of positive-versus-negative words.

Classifying articles into topics such as analyst recommendations, financial information, and acquisitions and mergers, the researchers compare days with no news, unidentified news, and identified news. They show that stock-level volatility is similar on no-news days and unidentified news days, which is consistent with the idea that the intensity and importance of information arrival is the same across these days. In contrast, the volatility of stock prices on identified news days is over twice that of other days.

Furthermore, the results are consistent with the idea that identified news days contain price-relevant information. Another finding is that deals and partnership announcements tend to have very positive effects, while legal announcements tend to have negative effects. Moreover, some topics, such as analyst recommendations and financials, are much more likely to appear on extreme return days. This suggests that different topics may have different price impacts.

Boudoukh, Feldman, Kogan, and Richardson conclude that their methodology may be useful for a deeper analysis of the relationship between stock prices and information, especially on the behavioral side. “There is a vast literature in the behavioral finance area,” they write, “arguing that economic agents, one by one, and even in the aggregate, cannot digest the full economic impact of news quickly. Given our database of identified events, it is possible to measure and investigate ‘complexity’ and its effect on the speed of information-processing by the market.“

Here’s the abstract of the paper:

A basic tenet of financial economics is that asset prices change in response to unexpected fundamental information. Since Roll’s (1988) provocative presidential address that showed little relation between stock prices and news, however, the finance literature has had limited success reversing this finding. This paper revisits this topic in a novel way. Using advancements in the area of textual analysis, we are better able to identify relevant news, both by type and by tone. Once news is correctly identified in this manner, there is considerably more evidence of a strong relationship between stock price changes and information. For example, market model R-squareds are no longer the same on news versus no news days (i.e., Roll’s (1988) infamous result), but now are 16% versus 33%; variance ratios of returns on identified news versus no news days are 120% higher versus only 20% for unidentified news versus no news; and, conditional on extreme moves, stock price reversals occur on no news days, while identified news days show an opposite effect, namely a strong degree of continuation. A number of these results are strengthened further when the tone of the news is taken into account by measuring the positive/negative sentiment of the news story.