WASHINGTON, Sept. 25 (UPI) -- The U.S. Department of Homeland Security is funding a research project designed to teach computers to scan text and then sort opinion from fact.
The project involves Cornell University Professor of Computer Science Claire Cardie and associate professors of computer science Janyce Wiebe of the University of Pittsburgh and Ellen Riloff of the University of Utah.
The consortium is one of four University Affiliate Centers to conduct research on advanced methods for information analysis and to develop computational technologies that contribute to national security.
"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."
The scientists will use machine-learning algorithms to give
computers examples of text expressing both fact and opinion and then
teach them to tell the difference.
Posting Guidelines | * Required fields
Hello, One can only salivate at the idea of this software beiing used to analyze, in real time, the talking heads , and better yet, the politicians. Imagine an on-screen box that showed the "percent fact" of what is being said. Lord, please let me live long enough to see this. Robert
Yeah, I'm supposed to believe that a computer, programmed by a government is going to be capable of discerning fact from fiction, that somehow the 'facts' it finds are going to be aligned with reality, not with 'Official Govenment Truth'. Ha, ha, ha. I needed a good laugh.
This is excellent news. Maybe once they figure out how to do this, they can teach the skill to the liberal news media.
I can see were this lead to the common computer knowlegde, Garbage In Garbage Out. Who is going to police the basic truth, far left wing professors?
Well finally we will be able to sort out the truth when we read what politicians have said. That will be a real joy -- seperating fact from fiction.
The news wires are in trouble now. In addition to my spam blocker I can install an opinion blocker. I might never get another never get another post from my UPI, AP, and Reuters RSS feeds!
Once they teach computers how to tell the difference between fact and opinion, maybe they can tackle the infinitely harder job of teaching the same thing to reporters.
Human being can not do, what these ... claim to be able to teach computer to do.
I suggest computer logic researchers touch base with the General Semantics community, since it teaches that words are only symbols - not reality! "The map is not the territory! - The picture is not the man! - The word is not the deed!" Some of their work is already done!
Because scientists are the regulators of fact or opinion! Try these on for size: He has stopped beating his wife. A human fetus is alive 4 weeks after conception. One could go on in throwing nice hurdles to choke the algorithm.
And once they finish that project, maybe they can create a computer program that can tell the difference between news articles based on reality and those based on utter nonsense. Like this one, for example.
Could you send one of these to 'The New York Times'?
Advertising Links
|
|
|
About UPI | Affiliates | Legal Disclaimer | Privacy Policy | Careers | Advertise Online | Contact Us