Web Science and Digital Libraries Research Group

The NFL Conference Championship games are this weekend and just one game separates the four remaining teams from Super Bowl XLVII. If you ignore the vapidity of the Te'o coverage, there is much discussion of how the loss of Rob Gronkowski will impact the performance of the Patriots this weekend. Aaron Hernandez should perform admirably and the entire team should be able to make up the difference and triumph. For our predictions we run a number of different types of algorithms in our research and compare the outputs. The three main algorithms that have consistently had the best performance are a Support Vector Model (SVM), a Multilayer Perceptron Neural Network, and a ranking algorithm. All three algorithms sided with the favorites. The SVM gives us a binary output, winner or loser. There is nothing in between. The SVM chose San Francisco and New England. The Neural Network output is a continuous variable that is supposed to be the margin of victory. A positive score fa

Three WS-DL classes are offered for the Spring 2013 semester: one undergraduate elective and two upper-level graduate courses. CS 418 Web Programming - This is a follow-on to last semester's Web Programming course .  This semester it will be taught by PhD student Scott Ainsworth , who has extensive experience in this area.  Students will learn to program in a LAMP environment .  CS 795/895 Applied Visual Analytics - Taught by Dr. Weigle , students will review basic data mining and information visualization techniques and then work together in groups on particular challenges from the visual analytics community . CS 895 Web-Based Information Retrieval - Taught by Dr. Nelson , this class will a review of IR models , ranking, evaluation, DM / ML , etc. CS 418 counts toward the Web Programming Minor , and the upper level graduate classes will count toward the 24 hours of course work required for the PhD.  The deadline to register is January 22 . --Michael

For the NFL Divisonal playoff week the predictions for all of our algorithms are in agreement. For our predictions we run a number of different types of algorithms in our research and compare the outputs. The three main algorithms that have consistently had the best performance are a Support Vector Model (SVM), a Multilayer Perceptron Neural Network, and a ranking algorithm. All three algorithms sided with the favorites except for Atlanta. All three picked Seattle for the upset. All season long our algorithms have consistently shown that Atlanta is over-rated. Yes they have won most of their games this season but they have had the easiest strength of schedule this year out of the all of the NFL teams. ESPN's adjusted strength of schedule shows that Atlanta has had an easy season. Big Lead Sports states that not only was Atlanta's season easy but it was respectively the easiest season for any NFL team in a number of years. Most of our algorithms take the strength of sched

The wildcard week of the playoffs is upon us. The numbers were crunched and the results were rather predictable. In three of the games the home is the favorite to win for both the Support Vector Model (SVM) and the PageRank model. For the fourth game the Seahawks were chosen by both the SVM and the PageRank model.  The SVM gives us a binary result so there is no degree or way to judge how close of a game it may be. Our numbers indicate that the Redskins Seahawks game is going to be close and probably a low scoring game. Both teams like to run the ball but the Seahawks defense has performed better that the Redskins this year. What my be interesting is that the Seahawks are a 2 to 3 point favorite and they are the visiting team. Our previous research has shown that home team underdogs are often a good bet to cover the spread. Vergin and Sosik found that not only has the home underdog been viable in some years but that the effect was more pronounced on nationally televised games ver