If a user conducts a search for, say, prostate cancer screening we can say these terms are linked. Now, if someone else searches for breast cancer screening you can see there are linkages between those three terms. But, you can also link back to the previous search via the terms cancer screening. So, why not map them? The below images are based on a really small sample of our clickstream data, but map the connections between search terms.
The above is based on a small sample of search terms around UTI. The one below uses a linked, but different technique:
You can see that there are different circle sizes (representing popularity of search) and some lines are thicker than others, showing these we searched together more often. Below is an easier to read sample of the above:
So what? Why am I sharing?
I can’t help feeling this is useful for highlighting search terms of interest for reviews. For instance, you may have 5 terms in your search, by harnessing the power of linked terms a system may suggest a further ten that may be useful! A form of query expansion perhaps?!