Slashdot is powered by your submissions, so send in your scoop


Forgot your password?
Check out the new SourceForge HTML5 internet speed test! No Flash necessary and runs on all devices. ×

Submission + - Researchers seek to sort facts from opinions

OffTheLip writes: The US Department of Homeland Security is funding research into teaching computers to distinguish opinions from fact in written text. Cornell University professor Claire Cardie and associates from other universities will use machine learning algorithms to scan text examples containing fact and opinion with the goal to distinguish the difference.

From the article:
"Lots of work has been done on extracting factual information — the who, what, where, when," explained Cardie. "We're interested in seeing how we would extract information about opinions."

Besides the obvious ramifications to the veracity of Slashdot discussions is this a good thing for US security?

I've looked at the listing, and it's right! -- Joel Halpern