Language models, classification and dbacl

Introduction

This is a non-mathematical tutorial on how to use the dbacl Bayesian text classifier. The mathematical details can be read here. This tutorial was revised for dbacl 1.11. As dbacl evolves, some statements below may become inaccurate, but reasonable effort is made to keep the tutorial synchronized.

dbacl is a UNIX command line tool, so you will need to work at the shell prompt (here written %, even though we use bash semantics). The program comes with five sample text documents and a few scripts. Look for them in the same directory as this tutorial, or you can use any other plain text documents instead. Make sure the sample documents you will use are in the current working directory. You need all *.txt, *.pl and *.risk files.

The tutorial below is geared towards generic text classification. If you intend to use dbacl for email classification, please read this.

• For the impatient
• Tips
• Language models
• Evaluating the models
• Decision Theory
• Using bayesol
• Miscellaneous
• Appendix A: memory requirements
• Appendix B: extreme probabilities