Duplicates and Keyword SPAM

For almost 2 years now, I implemented a duplicate checking algorithm at iSnare.com that checks each and every article to be reviewed against hundreds of thousands of our live articles. And since then I have been improving that algorithm to not just make it faster but also make it more effective and wiser… and guest what… it gets more than 90% of all duplicate contents.

Duplicate, in my definition is based on percentage of how much it duplicates an article already approved. And I have basis of a certain percentage on when to flag an article red (for disapproval) on the editor’s view.

Add comment February 5th, 2008