## A comparative analysis of offline and online evaluations and discussion of research paper recommender system evaluation

2013
##### Authors
Beel, Joeran
Genzmehr, Marcel
Langer, Stefan
Nürnberger, Andreas
##### Publication type
Contribution to a conference collection
##### Published in
Proceedings of the International Workshop on Reproducibility and Replication in Recommender Systems Evaluation / Alejandro Bellogin (ed.). - New York : ACM, 2013. - pp. 7-14. - ISBN 978-1-4503-2465-6
##### Abstract
Offline evaluations are the most common evaluation method for research paper recommender systems. However, no thorough discussion on the appropriateness of offline evaluations has taken place, despite some voiced criticism. We conducted a study in which we evaluated various recommendation approaches with both offline and online evaluations. We found that results of offline and online evaluations often contradict each other. We discuss this finding in detail and conclude that offline evaluations may be inappropriate for evaluating research paper recommender systems, in many settings.
##### Subject (DDC)
004 Computer Science
##### Keywords
Research paper recommender systems, evaluation, offline evaluation, click-through rate, online evaluation, comparative study
##### Conference
RepSys '13, Oct 12, 2013, Hong Kong
##### Cite This
ISO 690BEEL, Joeran, Marcel GENZMEHR, Stefan LANGER, Andreas NÜRNBERGER, Bela GIPP, 2013. A comparative analysis of offline and online evaluations and discussion of research paper recommender system evaluation. RepSys '13. Hong Kong, Oct 12, 2013. In: ALEJANDRO BELLOGIN, , ed.. Proceedings of the International Workshop on Reproducibility and Replication in Recommender Systems Evaluation. New York:ACM, pp. 7-14. ISBN 978-1-4503-2465-6. Available under: doi: 10.1145/2532508.2532511
BibTex
@inproceedings{Beel2013compa-31055,
year={2013},
doi={10.1145/2532508.2532511},
title={A comparative analysis of offline and online evaluations and discussion of research paper recommender system evaluation},
isbn={978-1-4503-2465-6},
publisher={ACM},
booktitle={Proceedings of the International Workshop on Reproducibility and Replication in Recommender Systems Evaluation},
pages={7--14},
author={Beel, Joeran and Genzmehr, Marcel and Langer, Stefan and Nürnberger, Andreas and Gipp, Bela}
}

RDF
<rdf:RDF
xmlns:dcterms="http://purl.org/dc/terms/"
xmlns:dc="http://purl.org/dc/elements/1.1/"
xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
xmlns:bibo="http://purl.org/ontology/bibo/"
xmlns:dspace="http://digital-repositories.org/ontologies/dspace/0.1.0#"
xmlns:foaf="http://xmlns.com/foaf/0.1/"
xmlns:void="http://rdfs.org/ns/void#"
xmlns:xsd="http://www.w3.org/2001/XMLSchema#" >
<dspace:hasBitstream rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/31055/1/Beel_0-285617.pdf"/>
<foaf:homepage rdf:resource="http://localhost:8080/"/>
<dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
<dc:creator>Beel, Joeran</dc:creator>
<dc:contributor>Genzmehr, Marcel</dc:contributor>
<dcterms:available rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2015-05-28T12:43:41Z</dcterms:available>
<dcterms:issued>2013</dcterms:issued>
<dc:language>eng</dc:language>
<dc:contributor>Langer, Stefan</dc:contributor>
<dc:creator>Gipp, Bela</dc:creator>
<dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
<dc:creator>Genzmehr, Marcel</dc:creator>
<dcterms:hasPart rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/31055/1/Beel_0-285617.pdf"/>
<dc:date rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2015-05-28T12:43:41Z</dc:date>
<dc:rights>terms-of-use</dc:rights>
<dc:contributor>Nürnberger, Andreas</dc:contributor>
<dcterms:abstract xml:lang="eng">Offline evaluations are the most common evaluation method for research paper recommender systems. However, no thorough discussion on the appropriateness of offline evaluations has taken place, despite some voiced criticism. We conducted a study in which we evaluated various recommendation approaches with both offline and online evaluations. We found that results of offline and online evaluations often contradict each other. We discuss this finding in detail and conclude that offline evaluations may be inappropriate for evaluating research paper recommender systems, in many settings.</dcterms:abstract>
<dc:creator>Langer, Stefan</dc:creator>
<dcterms:title>A comparative analysis of offline and online evaluations and discussion of research paper recommender system evaluation</dcterms:title>
<dcterms:rights rdf:resource="https://rightsstatements.org/page/InC/1.0/"/>
<bibo:uri rdf:resource="http://kops.uni-konstanz.de/handle/123456789/31055"/>
<dc:contributor>Gipp, Bela</dc:contributor>
<void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/>
<dc:contributor>Beel, Joeran</dc:contributor>
<dc:creator>Nürnberger, Andreas</dc:creator>
</rdf:Description>
</rdf:RDF>

No