@inproceedings{68747200812d4444abc03bd966441ca3,
title = "The combination and evaluation of query performance prediction methods",
abstract = "In this paper, we examine a number of newly applied methods for combining pre-retrieval query performance predictors in order to obtain a better prediction of the query{\textquoteright}s performance. However, in order to adequately and appropriately compare such techniques, we critically examine the current evaluation methodology and show how using linear correlation coefficients (i) do not provide an intuitive measure indicative of a method{\textquoteright}s quality, (ii) can provide a misleading indication of performance, and (iii) overstate the performance of combined methods. To address this, we extend the current evaluation methodology to include cross validation, report a more intuitive and descriptive statistic, and apply statistical testing to determine significant differences. During the course of a comprehensive empirical study over several TREC collections, we evaluate nineteen pre-retrieval predictors and three combination methods.",
keywords = "data mining, knowledge discovery, prediction methods",
author = "Claudia Hauff and Leif Azzopardi and Djoerd Hiemstra",
year = "2009",
month = mar,
day = "27",
doi = "10.1007/978-3-642-00958-7_28",
language = "English",
isbn = "9783642009570",
series = "Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)",
publisher = "Springer-Verlag",
pages = "301--312",
editor = "Mohand Boughanem and Catherine Berrut and Josiane Mothe and Chantal Soule-Dupuy",
booktitle = "Advances in Information Retrieval",
note = "31th European Conference on Information Retrieval, ECIR 2009 ; Conference date: 06-04-2009 Through 09-04-2009",
}