In the Chronicle of Higher Education, there is a troubling piece written by a fellow who writes and sells papers for/to students. Which got me to thinking: shouldn’t text analysis be able to solve this?
Here’s my thinking: I’m willing to bet every author produces unique combinations of words and phrases – a concept that Amazon for instance uses to improve its search functions (“statistically improbable phrases“). As the ‘ghost writer’ points out, most of the emails he gets from students are nearly illegible or otherwise atrocious. So – what if at the start of a school year, you sat all of your students down to handwrite a couple thousand words, any topic. Writing by hand is important, so that you get that student’s actual genuine writing. Scan it all in. Perform text analysis on it. Obtain a ‘signature’ for that student’s style. Then, when students submit their papers, analyze them again and compare the signatures. Where the signatures don’t match within a certain range, bring the student in to talk about their work. Chances are if they didn’t write it, they probably haven’t read it either…. Repeat each year to account for developing skill and ability.
Perhaps I’m naive, and text analysis isn’t at that level yet (but I’m willing to bet it could be…). If the problem is a student submits someone else’s work as his own, then maybe if we had a clear signal of his own true work, all this latent computer power sitting around could be brought into the equation…?
Just a thought.