Can Blogs and Tweets predict the future?
Hal Varian, Google’s chief economist, and his colleague Hyunyoung Choi think so. Researchers at Google used the frequency of certain search terms to forecast the sales of homes, cars and other products. Their research showed how the volume of searches for certain products, such as types of car, rose and fell in line with monthly sales. Google keeps extensive records of what is being searched which makes Varian and Choi’s method a far quicker way of gauging purchasing behavior than traditional sales forecasts, which are often made by looking back at purchasing patterns.
Other researchers have since analyzed search terms to look at all manner of behaviors. In late 2009, economists showed that the volume of searches for terms like “job search engine” is a good indicator of coming changes in the unemployment rate in the US. Researchers have also showed that tracking Google searches for consumer goods provided a better means of forecasting US retail sales than the traditional method of using surveys of consumer attitudes (Consumer Confidence Index). Now other sources, such as blog posts and tweets, are being mined too, and the variety of subject matter they address might mean that phenomena other than purchasing patterns can be explored.
For example, tweets may prove useful to political pollsters. Researchers at Carnegie Mellon University ran a sentiment analysis on tweets posted in the run-up to the 2008 presidential election relating to the candidates and used the results to try to assess voting intentions as the election neared. They found that this Twitter rating tracked more formal opinion polls closely. While they were not able to improve on the accuracy of those polls, the work did show that Twitter could provide a cheaper, quicker alternative.
It is no secret in advertising that the Web is a great way to see what people think about your brands, products or services. However, what if we used the Web to predict what products or services we launched on behalf of our brands?
Research has shown that blog posts, for example, can be used to predict stock market behavior. At the International Conference on Weblogs and Social Media in Washington, DC, researchers presented their findings that blogs can be used to create a measure of the frequency with which a range of words related to apprehension, such as “nervous” appear in posts. The researchers described how they have used the index to improve forecasts of the movement of the S&P 500. Other researchers have shown how Twitter may hold similar predictive power based on analysis of hundreds of millions of tweets that show increases in anxiety on their scale correlated with lower than expected stock prices. What is interesting is that very few of the posts and tweets were about stock trades, but instead capture the “national mood,” a collective feeling known to influence trading decisions.
The ability to use search engine terms, blog entries and tweets to make predictions about social and economic trends can help companies get ahead of the curve, especially in addressing anxiety. For example, Fannie Mae created a Website dedicated to helping people understand their options to avoid foreclosure. Rather than promote any one specific product, bloomfield knoble developed the site to specifically address anxiety index concerns based on national mood. Identifying the correlation between online information and real-world behavior is just one way to be proactive to the needs of clients.
# # #
bloomfield knoble creates marketing plans, strategy, creative design, collateral, Power Point presentations, email templates, videos, audio, music videos, television commercials, letterhead, identity, gift cards, SWOT analyses, brochures, letter templates, software applications, web applications, multimedia productions, Flash content, streaming videos, logo designs, widgets, technical consulting.