Blogger Sentiment Analysis
May 4, 2015 • Posted in Sentiment Indicators
Are prominent stock market bloggers in aggregate able to predict the market’s direction? The Ticker Sense Blogger Sentiment Poll “is a survey of the web’s most prominent investment bloggers, asking ‘What is your outlook on the U.S. stock market for the next 30 days?'” (bullish, bearish or neutral) on a weekly basis. The site currently lists 31 participating bloggers. Participation has varied over time. Because Ticker Sense collects data weekly, we look at weekly measurements and changes in weekly measurements. Because the poll question asks for a 30-day outlook, we test the forecasts against stock market behavior four weeks into the future. Because polling generally takes place Thursday-Sunday, we generally use the coincident Friday close to represent the state of the stock market for each poll. We use [% Bullish] minus [% Bearish] as the net sentiment measure for each poll. Using poll results from inception in July 2006 through mid-April 2015 (444 polls) and contemporaneous weekly closes of the S&P 500 Index as representative of the broad stock market, we find that:
The following chart compares the coincident S&P 500 Index and net blogger sentiment over the sample period (there were no surveys for 15 weeks during the sample period). On these visually comparable scales, blogger sentiment is generally more volatile than the stock market. The fairly large week-to-week swings in net blogger sentiment suggest either that the bloggers are very sensitive to changes in market conditions, or that participation in polling varies considerably across weeks. The average net blogger sentiment over the entire sample period is +6%.
For a more precise test of the relationship, we look at poll-to-poll changes in net blogger sentiment versus associated stock market returns.
The following scatter plot relates poll-to-poll changes in net blogger sentiment to weekly S&P 500 Index returns for concurrent intervals over the entire sample period. If bloggers as a group react to what just happened in the stock market, a best-fit line would run from the lower left to the upper right. Based on 443 poll-to-poll changes, there is some support for this hypothesis. The Pearson correlation for these two series is 0.32. The R-squared statistic for the relationship is 0.10, indicating that the change in the stock market over the past week explains 10% of the change in net blogger sentiment during that week.
How well does net blogger sentiment predict future stock returns?
The next scatter plot relates the four-week future S&P 500 Index return to weekly net blogger sentiment over the entire sample period.
- If net blogger sentiment forecasts stock market behavior, a best-fit line would run from the lower left to the upper right.
- If net blogger sentiment is a contrary indicator for stock market behavior, a best-fit line would run from the upper left to the lower right.
- If net blogger sentiment does not predict stock market behavior at all, the plot would show no pattern and a best-fit line would be flat.
Based on 439 observations, the data indicate that bloggers in aggregate do not predict the direction of the stock market. The Pearson correlation for the distribution is -0.15, and the R-squared statistic is 0.02. Blogger sentiment explains (in a contrarian direction) just 2% of the variation in stock returns over the next month.
For a different perspective and a test of linearity, we look at future returns by range of net blogger sentiment.
The next chart shows the average four-week future S&P 500 Index return by ranked fifth (quintile) of net blogger sentiment over the entire sample period. Each quintile represents 88 observations. Results generally confirm the negative correlation from the preceding regression, but the decline across quintiles is not completely systematic. Extreme sentiment readings (tail effects) drive the relationship.
Do the participating bloggers learn and improve over time?
The final chart plots the past 52-week rolling correlation between net blogger sentiment and four-week future S&P 500 Index return over the entire sample period. The darker dashed line is the best-fit linear trend line for this rolling correlation. If the bloggers as a group learn and improve over time (assuming stable group membership), the correlation should trend upward. Although the correlation varies, there is no evidence of long-run improvement in aggregate blogger forecasting performance. Instead, forecasting performance tends to become worse over time.
In summary, analysis of Ticker Sense Blogger Sentiment Poll results indicates that aggregate blogger sentiment, like many sentiment indicators, is perhaps slightly contrarian with respect to future stock market behavior.
Cautions regarding findings include:
- As noted, blogger participation in polling likely varies over time. Some types of forecasters may be more persistent in the participants than others.
- With a four-week future return calculation interval, the number of independent observations per quintile of net blogger sentiment and the number of independent observations per rolling 52-week correlation calculation are not large, limiting confidence in results.
- The number of independent 52-week correlation measurement intervals in the last chart is very small for inference.