New Tool to Detect AI-Generated Text
Sohni Rais, MS’25, information systems, has been researching and developing a tool to analyze writing and detect AI-generated text.
This article originally appeared on Northeastern Global News. It was published by Kate Rix. Main photo: Graduate student Sohni Rais helped develop a tool that uses unique aspects of human writing to sniff out AI-generated text. Photo by Matthew Modoono/Northeastern University.
Experts detect AI text by looking for human idiosyncrasies, like word variation and complex sentences
One of the things that AI doesn’t have that humans have in abundance is fingerprints.
Researchers at Northeastern University used the unique fingerprints of human writing — word choice variety, complex sentences and inconsistent punctuation — to develop a tool to sniff out AI-generated text.
“Just like how everyone has a distinct way of speaking, we all have patterns in how we write,” says Sohni Rais, a graduate student in information systems at Northeastern and a researcher on the project. In order to distinguish between human writing and AI text, she says, “we just need to spot the telltale patterns in writing style.”
AI text detection typically requires substantial computer power in the form of neural network transformers, says Rais, because these approaches analyze every letter, word and phrase in extreme detail. But this level of analysis isn’t necessary to distinguish between human and AI-generated text, Northeastern researchers say. In fact, the technically “lightweight” tool Rais helped develop can run on a regular laptop and is 97 percent accurate.
“We are not the first in the world who develop detectors,” says Sergey Aityan, teaching professor in Northeastern’s Multidisciplinary Graduate Engineering Program on the Oakland campus. “But our solution requires between 20 and 100 times less computer power to do the same job.”
Existing AI-text detecting services, including ZeroGPT, Originality and AI Detector, train large language models to analyze each word. Text entered into these tools is analyzed by proprietary algorithms trained with large datasets powered by transformers.
The lightweight tool can be trained by the user and live on their laptop, offering security and customizing advantages.
Read full story at Northeastern Global News