Using Taxonomic Domain Knowledge in Text Categorization Tasks

In this paper we present a “progressive filtering” technique aimed at improving the performances of a multiagent system devised to perform text categorization. The technique exploits the discriminant capabilities of multiple classifiers organized into a taxonomy and is aimed at coping with a problem that occurs very often in text categorization tasks, i.e. with the unbalance –for any category– between relevant and non relevant inputs. Experiments, conducted on RCV1-v2, highlight the validity of the approach.