@inbook {IOPORT.05887437, author = {Carmona-Cejudo, Jos\'e M. and Baena-Garc{\'\i}a, Manuel and del Campo-\'Avila, Jos\'e and Morales-Bueno, Rafael and Bifet, Albert}, title = {GNUsmail: open framework for on-line email classification.}, year = {2010}, booktitle = {ECAI 2010. 19th European conference on artificial intelligence, August 16--20, 2010 Lisbon, Portugal. Including proceedings of the 6th prestigious applications of artificial intelligence (PAIS-2010).}, isbn = {978-1-60750-605-8}, pages = {1141-1142}, publisher = {Amsterdam: IOS Press}, doi = {10.3233/978-1-60750-606-5-1141}, abstract = {Summary: Real-time classification of massive email data is a challenging task that presents its own particular difficulties. Since email data presents an important temporal component, several problems arise: emails arrive continuously, and the criteria used to classify those emails can change, so the learning algorithms have to be able to deal with concept drift. Our problem is more general than spam detection, which has received much more attention in the literature. In this paper we present GNUsmail, an open-source extensible framework for email classification, which structure supports incremental and on-line learning. This framework enables the incorporation of algorithms developed by other researchers, such as those included in WEKA and MOA. We evaluate this framework, characterized by two overlapping phases (pre-processing and learning), using the ENRON dataset, and we compare the results achieved by WEKA and MOA algorithms.}, identifier = {05887437}, }