Abbott's nutrition business has awarded GSLIS $25,000 for a project led by Assistant Professor Vetle Torvik titled, “Computer-assisted text-mining across biomedical papers and patents for competitive intelligence.” Working with Torvik on this year-long project is doctoral student Adam Kehoe (MS ’09).
With guidance from biomedical scientists at Abbott, Torvik and Kehoe will develop a new system for literature-based discovery that will draw on literature from both academia and industry. The goal is to create a system that will improve discovery in the realm of biomedical research by combining these two traditionally independent bodies of work. In addition to meeting Abbott’s specific research needs, the new tool will be made available online to external researchers.
“We are interested in what extra can we find when we put together these two separated literatures. Are there discoveries to be had when we put these things together?” said Torvik.
“Another interesting aspect is the collaboration between academics and industry. Academics don’t pay much attention to the patent literature, but industry pays a lot of attention to it, and they pay attention to the academic literature. There’s an asymmetry there. I’ve always been curious [about] the relationship between the academic literature and the patent literature, and...I think it’s really great that we have both sides at the table,” said Torvik.
Torvik is an assistant professor at GSLIS. His areas of expertise include mathematical optimization, computational statistics, text and data mining, literature-based discovery, and bioinformatics. He teaches courses on these topics, as well as informetrics, information processing, and literature-based discovery. Torvik earned a BA in mathematics from St. Olaf College, an MS in operations research from Oregon State University, and a PhD in engineering science from Louisiana State University.
Kehoe received his MS from GSLIS in 2009, after earning a bachelor of arts in history in 2007 from the State University of New York at Geneseo. Kehoe has consulted as a technologist for a number of nonprofit organizations. His previous graduate work primarily focused on technical and social aspects of public computing in urban areas. His current research interests include applications of machine learning in library and information science, particularly with respect to text mining and the biomedical literature.