Al Shiferaw has asked for the wisdom of the Perl Monks concerning the following question:

I need your brains out there to help me with this issue. I have a website that collects news from various sources on a given topic. What I like to do is come up with a simple algorithm to help me categorize by news titles(BTW, I am using a database). Example, given say 20 news titles. What can I do to dyamically categorized the simliar titles together. I know this can get complicated but I am looking for a simpler solution(if there is such a thing). Thanks!! Al

Replies are listed 'Best First'.
Re: algorithm to categorize
by perrin (Chancellor) on May 09, 2002 at 20:38 UTC
[reply]
Re: algorithm to categorize
by thelenm (Vicar) on May 09, 2002 at 20:39 UTC
    This doesn't seem particularly like a Perl question... Could you show us some code you've already written? If so, then the Monks might be able to offer some suggestions, but your question is broad enough that you probably won't get much help.

    You're looking for an algorithm to automatically classify texts based on their titles? Text classification (given an entire text) is a research area unto itself. My advisor got her Ph.D. doing text classification work. I'm sure that Google has lots of highly-paid professionals (or pigeons) doing their classification for them. Or software written by a talented team, anyway. :-)

[reply]
Re: algorithm to categorize
by Al Shiferaw (Initiate) on May 09, 2002 at 20:29 UTC
    BTW, here is an example to Google's news site. Notice that the have handled similar news items: http://news.google.com/news?q=money&hl=en
[reply]
A reply falls below the community's threshold of quality. You may see it by logging in.

Back to Seekers of Perl Wisdom