<p class="title">Scientists have created an artificial intelligence (AI) system that can accurately identify whether a student wrote their assignment on their own or got it penned by a ghostwriter.</p>.<p class="bodytext">Several studies have shown that cheating on assignments is widespread and becoming increasingly prevalent among high school students.</p>.<p class="bodytext">Researchers at the University of Copenhagen in Denmark have been working on ways to detect cheating on assignments through writing analysis by way of artificial intelligence have been underway for a few years.</p>.<p class="bodytext">Based on analyses of 130,000 written Danish assignments, scientists can, with nearly 90 per cent accuracy, detect whether a student has written an assignment on their own or had it composed by a ghostwriter.</p>.<p class="bodytext">The problem today is that if someone is hired to write an assignment, anti-plagiarism tools won't spot it, said Stephan Lorenzen, a PhD student at the University of Copenhagen.</p>.<p class="bodytext">"Our programme identifies discrepancies in writing styles by comparing recently submitted writing against a student's previously submitted work," Lorenzen said.</p>.<p class="bodytext">"Among other variables, the programme looks at word length, sentence structure and how words are used," said Lorenzen.</p>.<p class="bodytext">The programme, Ghostwriter, is built around machine learning and neural networks -- branches of artificial intelligence that are particularly useful for recognising patterns in images and texts.</p>.<p class="bodytext">The network is trained on large amounts of data to learn from representations of writing styles, which are then compared.</p>.<p class="bodytext">When a student submits an assignment, the network compares it against their previous assignments. For each previous assignment, the network provides a percentage score for writing style similarity against the new assignment.</p>.<p class="bodytext">In the end, a weighted average of these scores is calculated using a calculation that also takes other factors, such as delivery time, into account.</p>.<p class="bodytext">This final score is presented as a percentage and indicates the similarity between the new assignment and the student's writing style.</p>.<p class="bodytext">Ghostwriter's technological foundation can be applied elsewhere in society. For example, the program could be used in police work to supplement forged document analysis, a task carried out by forensic document examiners and others.</p>
<p class="title">Scientists have created an artificial intelligence (AI) system that can accurately identify whether a student wrote their assignment on their own or got it penned by a ghostwriter.</p>.<p class="bodytext">Several studies have shown that cheating on assignments is widespread and becoming increasingly prevalent among high school students.</p>.<p class="bodytext">Researchers at the University of Copenhagen in Denmark have been working on ways to detect cheating on assignments through writing analysis by way of artificial intelligence have been underway for a few years.</p>.<p class="bodytext">Based on analyses of 130,000 written Danish assignments, scientists can, with nearly 90 per cent accuracy, detect whether a student has written an assignment on their own or had it composed by a ghostwriter.</p>.<p class="bodytext">The problem today is that if someone is hired to write an assignment, anti-plagiarism tools won't spot it, said Stephan Lorenzen, a PhD student at the University of Copenhagen.</p>.<p class="bodytext">"Our programme identifies discrepancies in writing styles by comparing recently submitted writing against a student's previously submitted work," Lorenzen said.</p>.<p class="bodytext">"Among other variables, the programme looks at word length, sentence structure and how words are used," said Lorenzen.</p>.<p class="bodytext">The programme, Ghostwriter, is built around machine learning and neural networks -- branches of artificial intelligence that are particularly useful for recognising patterns in images and texts.</p>.<p class="bodytext">The network is trained on large amounts of data to learn from representations of writing styles, which are then compared.</p>.<p class="bodytext">When a student submits an assignment, the network compares it against their previous assignments. For each previous assignment, the network provides a percentage score for writing style similarity against the new assignment.</p>.<p class="bodytext">In the end, a weighted average of these scores is calculated using a calculation that also takes other factors, such as delivery time, into account.</p>.<p class="bodytext">This final score is presented as a percentage and indicates the similarity between the new assignment and the student's writing style.</p>.<p class="bodytext">Ghostwriter's technological foundation can be applied elsewhere in society. For example, the program could be used in police work to supplement forged document analysis, a task carried out by forensic document examiners and others.</p>