Mar 31, 2007

Keywords in CNN headlines

My friend read my last post, which talked about how 'sex' is so unusually high up on the NY searched keywords list, and he referred me to an interesting blog post. This friend of my friend, made a script that captures CNN headline keywords and then outputs a tag cloud. So the text cloud "contains the headlines of the past 30 days and is updated daily" according to the author.

The output over the past 30 days is an interesting follow-up to my post. Strangely enough, 'Food' leads the list. 'Iran', expectantly, also tops the list while 'Iraq' is not far behind. The word 'sex' has a count of 4, which is also interesting, as one would never assume 'sex' to be a biggest news of the day.

This is a cool tool. But what would be cooler, is if it would be possible to compile the same text cloud for BBC, Fox, Reuters, and some other leading Internet news providers. Comparing headline keywords from various sources would be quite indicative of what different companies find newsworthy or not.

No comments:

Post a Comment