On Sat, Jul 18, 2009 at 7:15 AM, Nick Arnett<nick.arn...@gmail.com> wrote:
> If you think there are no well-funded, successful companies in this domain,
> take a look at Nielsen/Buzzmetrics.  They've been at this for more than 10
> years.  They acquired my patents, from a startup where we demonstrated basic
> sentiment analysis in 2000 and 2001, showing that our software could rate
> the sentiment of Usenet movie reviews with 80 percent accuracy and forecast
> box office.

Netflix, even without the contributions of the contest teams, is doing
pretty well too. ;-)

> I would love to see more people tackling this kind of problem, but nobody is
> likely to succeed if they don't realize what has worked and what hasn't over
> the last decade and more.  Intelligence agencies and law enforcement have
> used relevant techniques for 20-30 years.  For example, traffic analysis is
> fundamental and doesn't require any NLP, just as the NSA is able to identify
> command and control centers by their behavior without having to decode a
> single encrypted transmission.  The danger of focusing on NLP and other
> really hard problems is that you fail to apply known techniques in new ways.
> Having said all that, I'll add that a lot of what I saw over the last few
> years in social media analytics was pretty eye candy without much behind
> it.  If that's all you look at, then yes, it seems quite shallow.  But I
> would hope that serious developers know that that's not all there is.  The
> systems I've built over the last decade have been based first on traffic
> analysis, then social network analysis, and last, text/lingustic analysis...
> and to do the latter well, humans were involved in the final summarization
> of topics, trends and so forth.

Man, it is so good to hear this from someone who's actually done it!
The other point, though, is that the "real thing", even traffic /
social network analysis, is compute-resource intensive and requires a
kind of programming knowledge that few have. So if something simple,
like emoticon counting, provides *some* clues about sentiment, it may
be worth doing. I'm not convinced, though, that it is worth doing.

M. Edward (Ed) Borasky

"I've always regarded nature as the clothing of God." ~Alan Hovhaness

Reply via email to