Research indexJournal article
Multi-class Text Categorization Based on Immune Algorithm
Zhang, Luo, Xue and 1 other
1 Dec 2008
NobleIDark:/48914/w1/20260523/7709D4DFDOI10.1109/ettandgrs.2008.337
Multi-class Text Categorization Based on Immune Algorithm
Zhang, Luo, Xue and 1 other · 2008 · Subscription
NobleIDark:/48914/w1/20260523/7709D4DFDOI10.1109/ettandgrs.2008.337
The full text is at the publisher
You can read the abstract here, or open it at the publisher.
Abstract
The nature of immune algorithm is to distinguish between self and non-self. On the basis of immune algorithm, we propose a new method of text categorization called the Clonal Selection Algorithm Based on Antibody Density (CSABAD). According to the clonal selection principle and density control mechanism, only those cells that have higher affinity and lower density are selected to proliferate. The ultimate classifier is composed with many memory cells. Because CSABAD is a two-class algorithm, we discuss the main approaches how to apply it to the multi-class problem, such as one-vs-one (OVO), one-vs-rest (OVR) and directed acyclic graph (DAG). Our experiments show that one-vs-one obtains the best classification performance on the 20_newsgroups dataset. In addition, the experiment results also show that it significantly outperforms Rocchio and Naive Bayes.