Welcome to the UPF Digital Repository

Exploring longitudinal effects of session-based recommendations

Show simple item record

dc.contributor.author Ferraro, Andrés
dc.contributor.author Jannach, Dietmar
dc.contributor.author Serra, Xavier
dc.date.accessioned 2021-02-09T16:40:25Z
dc.date.available 2021-02-09T16:40:25Z
dc.date.issued 2020
dc.identifier.citation Ferraro A, Jannach D, Serra X. Exploring longitudinal effects of session-based recommendations. In: RecSys '20: Fourteenth ACM Conference on Recommender Systems; 2020 Sep 22–26; Brazil. New York: Association for Computing Machinery; 2020. p. 474-9. DOI: 10.1145/3383313.3412213
dc.identifier.isbn 978-1-4503-7583-2
dc.identifier.uri http://hdl.handle.net/10230/46403
dc.description Comunicació presentada a: 14th ACM Conference on Recommender Systems celebrat del 22 al 26 de setembre de 2020 de manera virtual.
dc.description.abstract Session-based recommendation is a problem setting where the task of a recommender system is to make suitable item suggestions based only on a few observed user interactions in an ongoing session. The lack of long-term preference information about individual users in such settings usually results in a limited level of personalization, where a small set of popular items may be recommended to many users. This repeated exposure of such a subset of the items through the recommendations may in turn lead to a reinforcement effect over time, and to a system which is not able to help users discover new content anymore to the desirable extent. In this work, we investigate such potential longitudinal effects of session-based recommendations in a simulation-based approach. Specifically, we analyze to what extent algorithms of different types may lead to concentration effects over time. Our experiments in the music domain reveal that all investigated algorithms—both neural and heuristic ones—may lead to lower item coverage and to a higher concentration on a subset of the items. Additional simulation experiments however also indicate that relatively simple re-ranking strategies, e.g., by avoiding too many repeated recommendations in the music domain, may help to deal with this problem.
dc.format.mimetype application/pdf
dc.language.iso eng
dc.publisher ACM Association for Computer Machinery
dc.relation.ispartof RecSys '20: Fourteenth ACM Conference on Recommender Systems; 2020 Sep 22–26; Brazil. New York: Association for Computing Machinery; 2020.
dc.rights © 2020 Association for Computing Machinery
dc.title Exploring longitudinal effects of session-based recommendations
dc.type info:eu-repo/semantics/conferenceObject
dc.identifier.doi http://dx.doi.org/10.1145/3383313.3412213
dc.subject.keyword Session-based Recommendation
dc.subject.keyword Longitudinal Effects
dc.subject.keyword Bias
dc.rights.accessRights info:eu-repo/semantics/openAccess
dc.type.version info:eu-repo/semantics/acceptedVersion

Thumbnail

This item appears in the following Collection(s)

Show simple item record

Search DSpace


Advanced Search

Browse

My Account

Statistics

In collaboration with Compliant to Partaking