Search path visualization and session performance evaluation with log files

Authors:
Katrin Lamm;Thomas Mandl;Ralph Koellex
Affiliations:
Information Science, University of Hildesheim, Germany;Information Science, University of Hildesheim, Germany;Information Science, University of Hildesheim, Germany
Venue:
CLEF'09 Proceedings of the 10th cross-language evaluation forum conference on Multilingual information access evaluation: text retrieval experiments
Year:
2009

Citing 4
Cited 3

A focus+context technique based on hyperbolic geometry for visualizing large hierarchies

CHI '95 Proceedings of the SIGCHI Conference on Human Factors in Computing Systems
An empirical comparison of visualization tools to assist information retrieval on the Web

Journal of the American Society for Information Science and Technology
LogCLEF 2009: the CLEF 2009 multilingual logfile analysis track overview

CLEF'09 Proceedings of the 10th cross-language evaluation forum conference on Multilingual information access evaluation: text retrieval experiments
Search path visualization and session performance evaluation with log files

CLEF'09 Proceedings of the 10th cross-language evaluation forum conference on Multilingual information access evaluation: text retrieval experiments

Search path visualization and session performance evaluation with log files

CLEF'09 Proceedings of the 10th cross-language evaluation forum conference on Multilingual information access evaluation: text retrieval experiments
Which log for which information? gathering multilingual data from different log file types

CLEF'10 Proceedings of the 2010 international conference on Multilingual and multimodal information access evaluation: cross-language evaluation forum
Multilingual log analysis: LogCLEF

ECIR'11 Proceedings of the 33rd European conference on Advances in information retrieval

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper discusses new strategies for the performance evaluation of user search behavior. For the Log Analysis for Digital Societies (LADS) task of LogCLEF 2009 are proposed three different levels of user performance: success, failure and strong failure. The goal is to compare and measure session performance on a qualitative as well as on a quantitative level. The results obtained with both methods are in good agreement. Primarily they show that it is possible to investigate user performance from interpreting the user interactions recorded in log files. Both the qualitative and quantitative results give rise to a refinement of our operational definition of performance.