05821125

a

05821125 Mandl, Thomas Agosti, Maristella Di Nunzio, Giorgio Maria Yeh, Alexander Mani, Inderjeet Doran, Christine Schulz, Julia Maria LogCLEF 2009: The CLEF 2009 multilingual logfile analysis track overview. Peters, Carol (ed.) et al., Multilingual information access evaluation I. Text retrieval experiments. 10th workshop of the cross-language evaluation forum, CLEF 2009, Corfu, Greece, September 30 -- October 2, 2009. Revised selected papers. Berlin: Springer (ISBN 978-3-642-15753-0/pbk). Lecture Notes in Computer Science 6241, 508-517 (2010). 2010 Berlin: Springer EN

doi:10.1007/978-3-642-15754-7_62

Summary: Log data constitute a relevant aspect in the evaluation process of the quality of a search engine and the quality of a multilingual search service; log data can be used to study the usage of a search engine, and to better adapt it to the objectives the users were expecting to reach. The interest in multilingual log analysis was promoted by the Cross Language Evaluation Forum (CLEF) for the first time with a track named LogCLEF. LogCLEF is an evaluation initiative for the analysis of queries and other logged activities as expression of user behavior. The goal is the analysis and classification of queries in order to understand search behavior especially in multilingual contexts and ultimately to improve search systems. Two tasks were defined: Log Analysis and Geographic Query Identification (LAGI) which aimed at the identification of queries for geographic content and Log Analysis for Digital Societies (LADS) which was based on analyzing the user behavior of the search logs the service of The European Library. Five groups using a variety of approaches submitted experiments. The data for the track, the evaluation methodology and results are presented and discussed.