In its first year to compete, a team from UALR’s Donaghey College of Information Science and Systems Engineering competed with some of the worlds foremost computer schools in the NIST contest and was one of only five teams invited to present their work results at a November conference.
It was the first year for UALR to participate in the Text Retrieval Conference (TREC) organized by the National Institute of Standards. The UALR team – student Hemant Joshi and Professors Coskun Bayrak and Xiaowei Xu – competed against 28 others, including teams from John Hopkins University, Carnegie Mellon University, CSIRO ICT Centre in Australia, the University of Maryland at College Park, Indiana University, the University of Pisa, Italy, University of Amsterdam, NEC labs, the Chinese Academy of Sciences, University of Chicago, and more.
The information retrieval required teams to scour millions of blogs for specific pieces of information and rank each for relevancy. The UALR team was selected to present its work and results with the Information Retrieval community at November conference.
“For the opinion retrieval task – ranking blog posts by the most opinionated first, the median Mean Average Precision (MAP) is 0.1059 and UALR-IR group achieved performance of 0.0715,” said Herman Joshi, a Ph.D. candidate in in applied science, working under Bayrak’s supervision.
“We beat MAP scores by Chinese Academy of Sciences, National Institute of Informatics and Robert Gordon University in UK. Considering this was the first year for UALR participation, we feel satisfied with our performance.”
UALR’s master of science in information quality, a first in the world program developed by the University’s Donaghey College of Information Science and Systems Engineering in collaboration with MIT’s information quality program, will begin next year offering a distance learning version of the program world-wide.
The IQ program developed by UALR’s CyberCollege and MIT, with financial sponsorship from Acxiom Corp. in Little Rock, will begin a distance education component in collaboration with universities in Germany, Australia, and Hong Kong to make the program available on their campuses.
UALR began the program this year with an inaugural class of 25 students. Distant learning students will double the enrollment in UALR’s program next year.
“In many ways, we should not be surprised by the widespread interest in information and data quality,” says Dr. John Talburt, the graduate coordinator for the program.
“As public and private organizations world-wide increase their reliance on information for all aspects of their operation and decision making, the real costs of “dirty data” are increasing as well. Inaccurate, incomplete, inconsistent, and out-of-date information create operational errors, poor decisions, and damaged customer relations that cost government and industry billions of dollars a year.”
In November, Dr. Mary Good, dean of the UALR’s Donaghey College, delivered a progress report on the UALR IQ program at the 2006 International Conference on Information Quality at MIT, noting data quality is an emerging information science discipline.
The Association for Computing Machinery (ACM) recently launched the Journal of Data and Information Quality, major sign that IQ is becoming a separate discipline.
The new journal’s managing editor, Dr. Elizabeth Pierce, is a member of the UALR Information Science faculty.