For some background - if you follow us regularly you know that at MarketPsych we perform semantic analysis on 2 million articles daily from social and news media.  We have archives of such articles back to 1980 (1998 for the Thomson Reuters MarketPsych Indices).  Our software scans the content of each article in the news and social media flow and quantifies sentiments expressed about specific companies and locations.  Beyond sentiment, we also look for complex concepts such as GovernmentInstability and macroeconomic themes such as MonetaryPolicyLooseVsTight (a measure of easy versus tight monetary policy discussed in news and social media).  Several of the sentiments and themes we track appear predictive of future stock market movement globally.

Extracting emotion about different countries and locations from the business news is very difficult, especially when dealing with a firehose of unstructured information.  For example, we take special measures to exclude travel, entertainment, sports and other business-irrelevant sentiments.  Because all of the language we analyze is English, we are often quantifying an English-language cultural perspective on non-English-speaking countries.

In the Thomson Reuters Indices we produce sentiment for the 120 most economically significant countries.  The sentiments we issue are updated minutely.  You can see (with a magnifying glass!) the sentiments available below:

In today's newsletter I describe a series of studies we performed on our country sentiment data.  The descriptions are informal, as the research is still underway.  We are preparing a more formal research paper to describe the findings in detail with methodology. 

Note that when I say "our" and "we" in this newsletter, I generally mean Changjie Liu and his semi-magical R scripts.  In our first study we analyzed the 18 countries (for symmetry) with the top Buzz in the news over the past 14 years.  We then tracked the return of the major stock index of that country over the following year.  The list of countries with top Buzz is similar to expectations, as you can see in the list below:

For a given year, we ranked sentiment in each country for the year and went long the top 4 and short the bottom 4 for the ranked sentiment (Joy is inverted below).  Several sentiments stood out, in particular Joy, Fear, Government Instability, and MonetaryPolicyLooseVsTight.  For the sake of brevity I will focus on those in the remainder of this newsletter.

The below chart on the left indicates a 3-fold return from 1999 to June 2012 using a strategy that shorts the stock indexes of the 4 countries with the highest Joy and buys the 4 with the lowest Joy.  Even better, we see 10-fold returns if one buys the highest government instability and shorts those with the lowest government instability.  

Lesson to international investors so far?  Buy national unhappiness (low Joy) and GovernmentInstability, short Joy and government stability.

Note that our FinancialSystemInstability variable did not correlate strongly with returns, but our GovernmentAnger, RegimeChange, and ElectionSentiment (inverted) variables had correlations similar to GovernmentInstability.

These returns were interesting, and we wanted to establish their stability, so we also looked at arbitraging the top 2 vs bottom 2 and top 6 vs bottom 6.  See those results below for GovernmentInstability:

There was also a concern that perhaps the same countries were appearing on GovernmentInstability (e.g., Pakistan), and thus biasing the sample.  In fact, there were almost no countries remaining at the extremes of one of the ranking list over the entire 14 year period.  For Joy we see Italy and Spain dominating the high list, but for low, we don't see as much consistency overall.  Generally speaking, several countries and regions go into and out of the rotation for both the top and bottom groups, which supports sentiment as an independent region and country-selection tool.

We then examined stability of returns for the group of Countries with the largest Buzz over the past year, and we found better returns.  Buzz - a proxy for investor attention - appear to itself be a useful variable for improving country selection.

When we divided the group of countries into Developed vs Developing groups of nations, we continued to see return consistency.  Also we see consistency for a group of European countries only.   In fact, Joy led to much higher returns in Europe only.  The below chart depicts Joy arbitrage in the top 8 highest Buzz European countries, shorting the 2 with highest Joy and buying the 2 with lowest Joy.

We also found that dual-rankings of sentiments led to more stable, and still very good, performance:

We also looked at past stock index return.  There is a powerful mean-reversion effect of past one-year country returns, and arbitraging past return would earn a 5-fold return over our study period.  Fortunately, we found that this effect is independent (for most TRMI) from our sentiment strategies.

There is an interesting philosophical issue with Monetary Policy.  We see that a combination of high Joy and easy Monetary policy leads to greater underperformance.  Perhaps Joy is a proxy for overconfidence that leads to profligate spending and excessively low interest rates. National economic Joy may be good for politicians, but ultimately backfires for investors.

We figure a currency hedge can take care of currency risk in these strategies, but interest rate risk remains.  We will continue to explore the practicalities of implementing this strategy, and we will soon have a website displaying global investment risk by country based on news flow sentiment. 

This material is not intended as and does not constitute an offer to sell any securities or a solicitation of any offer to purchase any securities. 

The information of the MarketPsych Report is presented free of charge.  It is no substitute for the services of a professional investment advisor.  Investments recommended may not be appropriate for all investors.  Recommendations are made without consideration of your financial sophistication, financial situation, investing time horizon, or risk tolerance.  Readers are urged to consult with their own independent financial advisers with respect to any investment.

Past performance is no guarantee of future results.  Screen and model signals and related analysis are for informational purposes only and should not be construed as an offer to sell or the solicitation of an offer to buy securities.  Most financial instruments (stocks, bonds, funds) carry risk to principal and are not insured by the government.  Anyone using this newsletter for investment purposes does so at his or her own risk.

Data accuracy cannot be guaranteed.  Opinions and analyses included herein are based on sources believed to be reliable and written in good faith, but no representation or warranty, expressed or implied, is made as to their accuracy, completeness, timeliness, or correctness. We are not liable for any errors or inaccuracies, regardless of cause, or for the lack of timeliness of, or for any delay or interruptions in, the transmission thereof to the users.

As a matter of policy, we may act upon the investment information that this newsletter provides prior to making it available to the public.  We do not accept compensation of any kind from any companies mentioned herein.

MarketPsych is not responsible for any special, indirect, incidental, or consequential damages that may result from the use of, or the inability to use, the Information contained on this newsletter whether the Information is provided or otherwise supplied by MarketPsych or anyone else. Notwithstanding the foregoing, in no event shall MarketPsych total liability to you for any and all claims, damages, losses, and causes of action (whether in contract or tort or otherwise) exceed the amount paid by you, if any, for accessing this newsletter.

MarketPsych expressly disclaims all warranties and conditions with regard to the Web sites, their Content, and the Information, including, without limitation, all implied warranties and conditions of merchantability, fitness for a particular purpose, title, and non-infringement. By using the Web site, Content, and Information, I assume all of the risks associated with their use, and I release and agree to indemnify and hold harmless MarketPsych from any and all liability, claims for damages, and losses arising from or connected with such risks.

IF YOU DO NOT AGREE WITH ANY OF THESE TERMS AND CONDITIONS OR FIND ANY OF THEM TO BE UNACCEPTABLE, SIMPLY UNSUBSCRIBE FROM THE EMAIL LIST. If you understand and accept these caveats, feel free to read the newsletter.