Google just launched a new Google Labs product called Google Correlate, which looks at search trends, and attempts to apply them to real-world situations. The official description for Google Correlate is as follows:
Google Correlate is an experimental new tool on Google Labs which enables you to find queries with a similar pattern to a target data series. The target can either be a real-world trend that you provide (e.g., a data set of event counts over time) or a query that you enter.
It uses search activity data to find queries with a similar pattern to a target data series – the results of which can be viewed on the Google Correlate site (or downloaded as a CSV file).
“Google Correlate is like Google Trends in reverse,” Google says on an FAQ page. “With Google Trends, you type in a query and get back a data series of activity (over time or in each US state). With Google Correlate, you enter a data series (the target) and get back a list of queries whose data series follows a similar pattern.”
Users can upload their own data sets. When you upload one, (by US State or Time Series), Gogole Correlate will compute the “Pearson Correlation Coefficient” between your time series and the frequency time series for every query in its database.
Google provides a tutorial on how to use it here. There’s also a whitepaper.
Google suggests the time series data can be used to find things like what search terms are more popular in the winter, more likely to be issued in 2005, match the pattern of actual flu activity, etc. The state data can be used for things like what terms correlate with the state’s latitude, the annual rainfall in the state, being in New England, etc.
Interestingly the Labs experiment has its own Labs section, which so far only consists of one thing: search by drawing. It’s pretty cool. You can simply draw a pattern on the graph, and it will give you web search activity that closely matches the pattern you drew. I drew some random pattern, and Google found that it closely resembled US web activity for media player 10 codecs, for example.
Google says the data for Google Correlate is available from January 2003 to the present, with data being updated on a weekly basis.