Show simple item record

2017-03-24Konferenzveröffentlichung DOI: 10.18452/1441
Stereotype and Most-Popular Recommendations in the Digital Library Sowiport
dc.contributor.authorBeel, Joeran
dc.contributor.authorDinesh, Siddharth
dc.contributor.authorMayr, Philipp
dc.contributor.authorCarevic, Zeljko
dc.contributor.authorRaghvendra, Jain
dc.date.accessioned2017-06-15T13:05:33Z
dc.date.available2017-06-15T13:05:33Z
dc.date.created2017-03-24
dc.date.issued2017-03-24
dc.identifier.isbn978-3-86488-117-6
dc.identifier.urihttp://edoc.hu-berlin.de/18452/2093
dc.description.abstractStereotype and most-popular recommendations are widely neglected in the research-paper recommender system and digital-library community. In other domains such as movie recommendations and hotel search, however, these recommendation approaches have proven their effectiveness. We were interested to find out how stereotype and most-popular recommendations would perform in the scenario of a digital library. Therefore, we implemented the two approaches in the recommender system of GESIS’ digital library Sowiport, in cooperation with the recommendations-as-a-service provider Mr. DLib. We measured the effectiveness of most-popular and stereotype recommendations with click-through rate (CTR) based on 28 million delivered recommendations. Most-popular recommendations achieved a CTR of 0.11%, and stereotype recommendations achieved a CTR of 0.124%. Compared to a “random recommendations” baseline (CTR 0.12%), and a content based filtering baseline (CTR 0.145%), the results are discouraging. However, for reasons explained in the paper, we concluded that more research is necessary about the effectiveness of stereotype and most-popular recommendations in digital libraries.eng
dc.language.isoeng
dc.publisherHumboldt-Universität zu Berlin
dc.rights.urihttp://rightsstatements.org/vocab/InC/1.0/
dc.subjectevaluationeng
dc.subjectrecommendationseng
dc.subjectdigital librarieseng
dc.subjectrecommender systemseng
dc.subjectstereotypeeng
dc.subjectmost-popular recommendationseng
dc.subjectcontent-based filteringeng
dc.subject.ddc020 Bibliotheks- und Informationswissenschaften
dc.titleStereotype and Most-Popular Recommendations in the Digital Library Sowiport
dc.typeconferenceObject
dc.identifier.urnurn:nbn:de:kobv:11-100245250
dc.identifier.doihttp://dx.doi.org/10.18452/1441
local.edoc.container-titleEverything Changes, Everything Stays the Same? Understanding Information Spaces. Proceedings of the 15th International Symposium of Information Science (ISI 2017)
local.edoc.container-textErschienen in der Reihe "Schriften zur Informationswissenschaft", Band 70none
local.edoc.pages13
local.edoc.type-nameKonferenzveröffentlichung
local.edoc.institutionPhilosophische Fakultätnone
local.edoc.container-typebook
local.edoc.container-type-nameBuch
local.edoc.container-publisher-nameVerlag Werner Hülsbuschnone
local.edoc.container-publisher-placeGlückstadtnone
local.edoc.container-eventEverything Changes, Everything Stays the Same? Understanding Information Spaces. 15th International Symposium of Information Science (ISI 2017), Berlin, Germany, 13.03.2017 - 15.03.2017
local.edoc.container-periodicalpart-creatorMaria Gäde, Violeta Trkulja, Vivien Petras (Hrsg.)
local.edoc.container-firstpage96
local.edoc.container-lastpage108

Show simple item record