Abstract
Arabic is a major and a highly inflected language, and thus requires good stemming for effective text mining. Yet no standard approach to stemming has emerged. This work investigates some of the issues involved in achieving multilingual text mining (MTM). This work is based on Self-Organizing Map (SOM) and uses Arabic/English corpus as the test-bed. Issues related to Arabic/English text mining, stemming and clustering are discussed in this paper. In the authors knowledge there is no significant literature available regarding SOM technique applied to Arabic and English languages text mining.