Feed Distillation Using AdaBoost and Topic Maps

This paper retains the experiences by participating in TREC 2007 Blog Track ‘Feed Distillation’. To perform the run various classifiers are combined, which analyze title-, content- and splog-specific features to predict the relevance of a feed related to a topic, based on the idea of AdaBoost. The implemented classifiers utilize keywords retrieved from different thesauri such as Wordnet and Wortschatz, as well as from websites providing hierarchical organized ‘ontology’ such as the ‘Open Directory Project’ and Yahoo Directory. To structure the keywords, Topic Maps are utilized according to ISO/IEC 13250:2000.

• Type: Conference
• Year: 2007
• Where: TREC
• Authors: Wai-Lung Lee, Andreas Lommatzsch, Christian Scheel
• Keywords: Classifiers Utilize Keywords, Track ‘feed Distillation, TREC 2007, TREC 2007 Blog, TREC 2008