Olex: Effective Rule Learning for Text Categorization

This paper describes Olex, a novel method for the automatic induction of rule-based text classifiers. Olex supports a hypothesis language of the form "if T₁ or hellip or T_n occurs in document d, and none of T_1+n,... T_n+m occurs in d, then classify d under category c," where each T_i is a conjunction of terms. The proposed method is simple and elegant. Despite this, the results of a systematic experimentation performed on the REUTERS-21578, the OHSUMED, and the ODP data collections show that Olex provides classifiers that are accurate, compact, and comprehensible. A comparative analysis conducted against some of the most well-known learning algorithms (namely, Naive Bayes, Ripper, C4.5, SVM, and Linear Logistic Regression) demonstrates that it is more than competitive in terms of both predictive accuracy and efficiency.