The University of Copenhagen researchers recently used big data and artificial intelligence together, to determine whether a student wrote his assignment by his own or copied it from somewhere else- with nearly 90 percent accuracy. Cheating has always been a major problem in front of the school when students have started to indulge in the practices of copying assignments from somewhere else without writing them on their own. Assignment cheating is the most widespread and is becoming increasingly common among high school students. To combat the same issue, till now the University of Copenhagen used to detect cheating on assignments through writing analysis by way of artificial intelligence, which was somewhere not much effective. But, using the new program 'ghostwriter', scientists can now, with nearly 90 percent accuracy, detect whether a student has written an assignment on their own or had it composed by someone else.
Danish high schools currently use the Lectio platform to check if a student has handed over a plagiarized assignment or not. But, it takes a harder time to discover if a student has copied it from somewhere else.
"The problem today is that if someone is hired to write an assignment, Lectio won't spot it. 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.'," explains Ph.D. student Stephan Lorenzen of the Department of Computer Science.
The new program, Ghostwriter, is built around machine learning and neural networks which are particularly useful for recognizing patterns in images and texts. The new program, Ghostwriter is still a research project at the Department of Computer Science and will be implemented soon by the universities, in the future. There are some discussions that needed to be done on it, before taking a major move.
"I think that it is realistic to expect that high schools will begin using it at some point. 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," believes Lorenzen.
It would be unfair to say that the new program, Ghostwriter can only be implemented in checking the plagiarism of the assignment when the technology can be leveraged in any other field as well. The technology can be applied even in the police work also to supplement forged document analysis, a task carried out by forensic document examiners and others.
"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. We can look at large amounts of data and find patterns. I imagine that this combination would benefit police work," says Lorenzen, who emphasizes that ethical discussions are needed here as well.
Also, the technology can be applied to analyze Twitter tweets to determine whether they were composed by actual users or penned by paid imposters or robots. The technology has a wide scope and can be leveraged in any field to check plagiarized content or fraud content.
About the Ghostwriter program:
The Ghostwriter program uses Siamese neural network to distinguish the writing styles of two texts.
The network compares the assignment with the previous assignments and provides a percentage score for writing style similarity against the new assignment.
The research group behind the result is DIKU-DABAI (Danish Center for Big Data Analytics-driven Innovation). The group is headed by Professor Stephen Alstrup.