CSC 560: Special Topics in Databases: Web Mining
Spring 2009

Instructor: Alexander Dekhtyar, dekhtyar@calpoly.edu, 14-215

Office Hours:
When
Who Where
Monday 8:30am - 9:30am Alex 14-215
Wednsday 8:30am - 9:30am Alex 14-215
Thursday 9:00 - 12:00pm Alex 14-215

Additional appoinments: send email.

Final Exam Date: Monday, December 7, 2009, 4:10 - 7:00pm

(note: there is no final exam, but will do project presentations in that time)

News and Notes

Old News and Notes

Course Materials

Syllabus Postscript PDF
CSC 560 Wiki HTML
Datasets Wiki HTML
Competitions INEX XML Mining ICDM (brain)

Project

Stage 1 Due: September 28, 2009 Team formation Postscript PDF [September 22, 2009]
Stage 2 Due: October 21, 2009 Project Proposal Postscript PDF [September 27, 2009]

Assignments

Stage 1 Due: October 7, 2009 In-class presentation topic selection Postscript PDF [September 22, 2009]
Stage 2 Due: October 26, 2009 Reading list Postscript PDF [October 13, 2009]
Stage 2 Due: November 9 - December 4, 2009 Presentation Postscript PDF [October 26, 2009]

Lecture Notes

Lecture 0 (*) September 23 What is KDD? Postscript PDF [September 22, 2009]
Lecture 0 (*) September 23 What is Data Mining? Postscript PDF [September 22, 2009]
Lecture 1 September 23 What is Web Mining? Postscript PDF [September 22, 2009]
Lecture 2-1 (*) September 28 Data Mining Recap:Classification. C4.5. Postscript PDF [September 22, 2009]
Lecture 2-2 (*) September 28 Data Mining Recap:Classification: Beyond C4.5. Postscript PDF [September 22, 2009]
Lecture 3-1 (*) October 1 Data Mining Recap:Clustering. K-means Postscript PDF [September 22, 2009]
Lecture 3-2 (*) October 1 Distance Measures Postscript PDF [September 22, 2009]
Lecture 3-3 (*) October 1 Clustering: Hierarchical Postscript PDF [September 22, 2009]
Lecture 4-1 October 5 Link Analysis Postscript PDF [October 5, 2009]
Lecture 4-2 October 5 Link Analysis: PageRank Postscript PDF [October 5, 2009]
Lecture 4-3 October 5 Link Analysis: PageRank Math Postscript PDF [October 5, 2009]
Lecture 6 October 14 Community Discovery Postscript PDF [October 26, 2009]
Lecture 7 October 21 Web Usage Mining Postscript PDF [October 26, 2009]
Lecture 8-1 October 26 Naive Bayes Postscript PDF [September 28, 2009]
Lecture 8-2 October 26 Naive Bayes for Text Classification Postscript PDF [October 26, 2009]
Lecture 9 October 26-28 E-M algorithm Postscript PDF [October 26, 2009]
Lecture 10 November 2 Support Vector Machines: Linearly Separable case Postscript PDF [November 2, 2009]

November 2 2009, dekhtyar at csc.calpoly.edu