Mid-cap Stocks Hold Most Value When Investing Based on News Sentiment

RavenPack | September 27, 2012

Measuring the sentiment on companies from news provides value beyond traditional quantitative factors in a stock selection process.

Executive Summary:

In this report, we construct a company sentiment indicator from news, and look at how prices are impacted over several investment horizons. Below are some of our key results:

Performance Differs Across Size When Trading on Sentiment

  • Applying a sentiment-based strategy on small and mid cap U.S. stocks yields equal-weighted annualized returns of 24.5% and 20.5% over a 1 week and 1 month investment horizons - with information ratios of 2.85 and 1.94
  • Focusing on large cap U.S. stocks, the sentiment-based strategy yields equal-weighted annualized returns of 6.2% and 2.5% over a 1 week and 1 month investment horizon – with information ratios of 1.22 and 0.42

Stock Prices Overreact to Extreme Positive Sentiment

  • Companies with extreme positive sentiment over the past month tend to revert in the following month
  • The reversal effect is stronger for mid cap than for large cap stocks

Stocks with Negative Sentiment Underperform Positive Sentiment Stocks

  • Stocks with extreme positive sentiment tend to revert over time
  • The return spread between positive and negative sentiment stocks is greater for mid cap than for large cap stocks
  • Negative sentiment stocks consistently underperform positive sentiment stocks both over time and across size


With the continuous innovations made in news analytics, it has become more easily attainable for investors to make their models news aware – both when it comes to scheduled and unscheduled news. Incorporating news into an investment framework is desirable, since in theory, news affects risk and return expectations - and consequently the pricing of securities. Although, the concept of applied news analytics has been around for more than a decade, we are still in an early stage in understanding different trading and investment applications. As part of our continued research efforts, it’s our objective to help shed some light on this topic.

Recently, we considered how changes in company sentiment could be useful for shortterm stock selection - especially, when focusing on intraday and up to 2 days after a significant change in a company’s sentiment. In this paper, we build on this idea, and extend our analysis to the medium-term considering investment horizons of 1 week to 1 month. The methodology disclosed here is similar to one shared in a previous study, except we now look at sentiment levels rather than sentiment changes. In addition, we try to: a) capture directional sentiment strength, and b) adjust for size and sector news flow differences.

Our research is based on the RavenPack News Analytics 3.0 dataset, a real–time news analytics service that covers more than 30,000 publicly traded companies worldwide. The archive extends back to 2000 with more than 12 years of millisecond timestamped historical data.

In the next section, we will briefly describe the construction of a RavenPack Company Sentiment Indicator and look at some of its basic characteristics. Later we present the future return pattern following positive and negative sentiment values and consider the effect of size on signal performance. We also illustrate the economic significance of a trading strategy based on the sentiment indicator and reveal our conclusions.

By providing your personal information and submitting your details, you acknowledge that you have read, understood, and agreed to our Privacy Statement and you accept our Terms and Conditions. We will handle your personal information in compliance with our Privacy Statement. You can exercise your rights of access, rectification, erasure, restriction of processing, data portability, and objection by emailing us at privacy@ravenpack.com in accordance with the GDPRs. You also are agreeing to receive occasional updates and communications from RavenPack about resources, events, products, or services that may be of interest to you.

Data Insights

Read More