You are viewing a single comment's thread from:
RE: Using Machine Learning to Fight Plagiarism
Surely this would not work if you can only train the model on what the steemit user is posting?
The corpus you use to build the model in the case of a serial plagiarist will consist of several different posts, but when you train your model you'll end up with a model of the kind of posts that person plagiarises - there'll be no way to detect the odd ones out.