There’s big business in selling essays to students with deep pockets. But an artificial intelligence (AI) program could put an end to the technically-legal-but-morally-grey practice.

Researchers at the University of Copenhagen say they have developed an AI program that can determine whether an essay is written by a ghostwriter with nearly 90% accuracy.

The program, dubbed Ghostwriter, uses machine learning and neural networks to compare an essay with a student’s previous work.

It looks at factors such as language and sentence structure and hunts for differences that indicate a different writer.

It also takes factors such as delivery time into account and provides an overall percentage score for the student’s writing style similarity against the new assignment.

Existing plagiarism detectors, such as Lectico, check an essay for direct copying of passages from previously submitted essays. As a result, they struggle to detect if it has been written by someone else.

How well do you really know your competitors?

Access the most comprehensive Company Profiles on the market, powered by GlobalData. Save hours of research. Gain competitive edge.

Company Profile – free sample

Thank you!

Your download email will arrive shortly

Not ready to buy yet? Download a free sample

We are confident about the unique quality of our Company Profiles. However, we want you to make the most beneficial decision for your business, so we offer a free sample that you can download by submitting the below form

By GlobalData
Visit our Privacy Policy for more information about our services, how we may use, process and share your personal data, including information of your rights in respect of your personal data and how you can unsubscribe from future marketing communications. Our services are intended for corporate subscribers and you warrant that the email address submitted is your corporate email address.

“The problem today is that if someone is hired to write an assignment, Lectio won’t spot it,” explains PhD student Stephan Lorenzen at the University of Copenhagen’s Department of Computer Science.

“Our program identifies discrepancies in writing styles by comparing recently submitted writing against a student’s previously submitted work. Among other variables, the program looks at: word length, sentence structure and how words are used. For instance, whether ‘for example’ is written as ‘ex.’ or ‘e.g.’.”

Big data to catch big cheats

The AI program was trained using a dataset of 130,000 written assignments from 10,000 different high school students. From this big data, the AI – known as a Siamese neural network – was able to learn and compare the differences between different writing styles.

Essay ghostwriting services aren’t just big business in Denmark; essay writing service UK Essays says it sold 16,000 assignments in 2016 and that figure is believed to be on the rise. A 5,000 word essay at a 2:1 grade can cost anywhere from £600 to more than double that, depending on a range of factors such as turnaround time.

While Lorenzen believes it might not be long before the AI program could be used in schools to catch cheats, it shouldn’t be considered a silver bullet.

“I think that it is realistic to expect that high schools will begin using it at some point,” he said. “But before they do, there needs to be an ethical discussion of how the technology ought to be applied.

“Any result delivered by the program should never stand on its own, but serve to support and substantiate a suspicion of cheating.”

AI catches essay cheats… and one day criminals?

Ghostwriter could also be applied to other areas on society, added Lorenzen.

“It would be fun to collaborate with the police, who currently deploy forensic document examiners to look for qualitative similarities and differences between the texts they are comparing,” he said. “We can look at large amounts of data and find patterns. I imagine that this combination would benefit police work,”

The same type of AI has already been used to determine whether Tweets are composed by humans or bots.

The paper, titled ‘Detecting Ghostwriters in High Schools’, can be found here.

The research group behind the project is the Danish Center for Big Data Analytics driven Innovation. It was supported by Innovation Fund Denmark.


Read more: AI whisky signals machine creep into craftsmanship – but will consumers resist?