Listen: High School Cheaters Nabbed By Neural Network
"This is scientific American sixty seconds science. I'm Christopher Dodd Yata, the English language version of Wikipedia has almost six million articles. And if you're cheating student that's six million essays already written for you footnotes and all except plagiarism isn't really ineffective tactic just plug the text into a search engine and game over. But what about having a ghostwriter at a paper mill composer final essay, STAN dot K two recent software cannot detect this kind of cheating. Stefan luanne is a data analyst at the university of Copenhagen in Denmark, where he's based ghost writing is a growing problem in high schools, so Lawrenson and his colleagues created a program called ghost rider that can detect the cheats at its core is in neural network trained and tested on a hundred and thirty thousand real essays, from ten thousand Danish students after reading through tens of thousands of essays label as being written by the same author or not the machine taught itself to tune in to the characteristics. That might tip off cheating, for example, did a student's essays share the same styles of punctuation. The same spelling mistakes were the abbreviations, the same by scrutinizing inconsistencies like those ghost rider was able to pinpoint cheated essay nearly ninety percent of the time, the team presented the results at the European symposium on artificial neural networks, computational intelligence and machine learning. And there is one more aspect here that could help students your high school, essays presumably, get better over time as you learn to write and the machine can detect that the final idea is, of course, to try to detect students who either at risk, the because that development and writing style is not as you would expect teachers could thus give extra help to kids who really need it while sniffing out the cheaters too. Thanks for listening for scientific American sixty seconds science. I'm Christopher Don yada."