DIMACS Working Group on Monitoring Message Streams

Retrospective and Prospective Event Detection

This working group meets every two weeks and comprises DIMACS researchers working on the project "Monitoring Message Streams: Retrospective and Prospective Event Detection." The National Science Foundation supports this project through its KDD program. Fred Roberts is the principal investigator. Paul Kantor is the project coordinator. The group is interested in topics such as:

• large-scale text categorization
• streaming data
• dimensionality reduction

Schedule and Personnel

• Members of the Working Group
• Summer 2002 schedule
• Fall 2002 schedule

Project Reports

Viewing reports marked with a requires a password. Please contact madigan@stat.rutgers.edu, roberts@dimacs.rutgers.edu, or kantorp@cs.rutgers.edu for access.

• Project Overview (PS) (PDF) (DOC)
  Paul B. Kantor and Fred S. Roberts, November 2002.

• Towards Fast, Effective Nearest Neighbor Text Classification (PS) (PDF)
  David D. Lewis, S. Muthukrishnan, R. Ostrovsky, M. Strauss, November 2002.
• Distances from Sketches (PS) (PDF)
  Martin Strauss, November 2002.
• Sparse Bayesian Classifiers for Text Categorization - Batch Learning (PS) (PDF)
  David Madigan, David D. Lewis, and Alexander Genkin, November 2002.
• Sparse Bayesian Classifiers for Text Categorization - Online Learning (PS) (PDF)
  David Madigan and Wen-Hua Ju, November 2002.
• Combinatorial Clustering for Textual Data Representation in Machine Learning Models
  Andrei Anghelescu and Ilya Muchnik, November 2002.
• An Experimental Evaluation of a Combinatorial Clustering Model for Textual Data Representation
  Andrei Anghelescu and Ilya Muchnik, November 2002.
• A Simple, Course Vector Nearest Neighbors Algorithm (PS) (PDF)
  S. Muthukrishnan, November 2002.
• Some Statistical Analysis Algorithms on Data Streams (PS) (PDF)
  S. Muthukrishnan, November 2002.
• Notes on Term Selection
  Endre Boros, November 2002.
• Training a Rocchio classifier for adaptive filtering (PS) (PDF)
  Andrei Anghelescu, David D. Lewis, Vladimir Menkov, and Paul Kantor, TREC 2002.
• Feature Selection and Batch Filtering (PS) (PDF)
  Endre Boros and David J. Neu, TREC 2002.
• CCR-DIMACS Workshop
  Bob Grossman, Paul Kantor, and Muthu Muthukrishnan, June 2002.

Online Tools

• Current Comparison Tool
  
• Eye of Deity Tool
  
• Histogram Tool

Project Presentations

• Feature Selection
  Endre Boros, November 2002.
• Project presentation (PPT), August 2002
• Project presentation (PPT), May 2002
• Project proposal (Word), March 2002

Related Events

• TREC 2002 Conference
• June 17-22, CCR/DIMACS Workshop/Tutorial on Mining Massive Data Sets and Streams: Mathematical Methods and Algorithms for Homeland Defense

Papers

• Madigan
• Muthukrishnan
• Ostrovsky 1 2 3 4