CS539 MACHINE LEARNING. SPRING 99
PROJECT 3
Naive Bayes Classification

PROF. CAROLINA RUIZ
Department of Computer Science
Worcester Polytechnic Institute

• Project Description
• Project Assignment
• Report Submission and Due Date

1. Classification of Newsgroup Articles. (100 points) For this, you just need to follow the steps of the training process described on Section 6.10 of the textbook. You should reproduce their experimental results. You may find it useful to read the statement of Mitchell's Assignment 6. The Rainbow source code and newsgroups dataset are available online.

2. EXTRA-CREDIT (25 points) Use the Rainbow code (or write your own code if you prefer) to construct a naive Bayes classifier for the Census-income data from Project 1. Compare the results that you obtain by using naive Bayesian classification over the training data with those that you obtained in your project 1. Discuss the advantages and disadvantages of using naive Bayes classification instead of decision trees for this learning task.

• Program. You should submit any modifications done to the Rainbow code, or your own code if you didn't use Rainbow by email to ruiz@cs.wpi.edu.

• Written Report. Please bring your report to my office (FL232) or to class by the due date/time. Your report should discuss the following issues:
  1. adaptation of the code (if any) or a description of your own code,
  2. the experiments you ran with the system,
  3. experimental results,
  4. evaluation of the accuracy of the system over the training data,
  5. strengths and the weaknesses of your system.
  Your report should also include a short user manual explaining how to install, run, and use your system (if different from the CMU package).

• Oral Report. We will discuss the results from the individual projects during the class on March 23. Be ready to show your results (I strongly encourage you to prepare transparencies) and to discuss your project solution in class.