Tentative Schedule
EE 380L:  A Practicum in Data Mining (Mining the Web)
Spring 2003

1. Introduction (1 lecture)
   
2. Hyperlink Structure of the Web (3 lectures)
   • Google's PageRank algorithm
   • Web Structure (Bowtie)
   • Hubs & Authorities

   paper discussions: 2 classes

3. Web Content Mining (5 lectures)
   • Introduction to information retrieval
   • GVSM, LSI
   • Evaluation; TREC
   • Query expansion; relevance feedback
   • Document clustering; Graph Partitioning
   • Text Classification; SVMs
   • Web based IR
   • Managing Gigabytes
   • Analysis of XML documents
   • Search Engines: combining (meta)text and link analysis
     paper discussions: 4 classes
4. Web Usage Mining (4 lectures)
   • Clickstream Analysis
   • Personalization (recommender systems, personal agents)
   • Adaptive Web sites
   • Distributed and Mobile computing
   • E-commerce Applications
     paper discussions: 3 classes
5. Term Paper Presentations (3 classes)