Java Programming

I have to write a program which will analyse pieces of text, (e.g. student essays) for similarity ( plagiarism ) with each other and relevant articles on the web. The latter part has to be done using Information retrieval ideally.

I'm not a great java programmer so I was hoping that people who are could give me a hand, or at least a point in the write direction ( useful example code, type of java to use etc. ).

I hope ye can help. Thanks!
Shotsyjr