Researchers from the Virginia Bioinformatics Institute have created a seek-and-destroy program -- for plagiarism.
Called ET Blast (www.ETBlast.org), it's designed to find plagiarism in scientific papers, It does a full-text analysis, and then looks for similar publications in several databases.
The site was originally designed to improve a researcher's access to literature, but was since adapted to seek out copied research.
The full text analysis determines how much of a complete original paper was taken and used by another author. The researchers created a sub-website from ET Blast, called Déjà vu, showing examples of plagiarized work. While many of the similar articles on Déjà vu are from the same author, as one would expect, a number of them are from different authors.
Harold "Skip" Garner, executive director of the Virginia Bioinformatics Institute, authored a paper explaining the process which will appear in PLoS ONE. Thus far, Garner and his team have created ET Blast for biomedical literature only. He said the site is still mainly designed to assist researchers in finding similar articles on their subject.
Follow us
"Its intent is not to detect plagriasm," Garner said. "However, since ET Blast returns and scores results on similarity, if something is similar it will be on the top of the list and will be obvious."
Unlike plagiarism detectors, such as Turnitin.com, he said ET Blast uses different databases for comparative analysis. "We have better literature," Garner said. "There are abstracts and full papers, and a database called Crisp, where you compare stuff to every grant the NIH gets. It's compared to any research that's been funded."
The technology allowing ET Blast to do its full text analysis is called Helio Text. Unlike other plagiarism detectors, it does not use phrases or similar words to check for copying. Helio Text actually looks at the entirety of the text.
The issue of plagiarism is a vital one in the biomedical industry, says Garner. "A lot of clinicians will make their decisions on how to treat patients based on their review of medical literature. It's important that the doctor has reliable literature. Doctors won't make decisions based on plagiarized papers. Papers with plagiarism and other unethical, inflating data can cause researchers to make sub optimal decisions and delay discoveries," Garner said.
Garner said that the technology behind ET Blast could work for any literature or business sector, not just limited to biomedical research. "We have the capability to build this for any sector, either public or propriety," Garner said.