Recommender systems may enhance the discovery of novelties

Recommender systems are vital for shaping user online experiences. While some believe they may limit new content exploration and promote opinion polarization, a systematic analysis is still lacking. In this paper we present a model that explores the influence of recommender systems on novel content...

Full description

Saved in:
Bibliographic Details
Main Authors: Giordano De Marzo, Pietro Gravino, Vittorio Loreto
Format: Article
Language:English
Published: IOP Publishing 2024-01-01
Series:Journal of Physics: Complexity
Subjects:
Online Access:https://doi.org/10.1088/2632-072X/ad9cdd
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850123222311239680
author Giordano De Marzo
Pietro Gravino
Vittorio Loreto
author_facet Giordano De Marzo
Pietro Gravino
Vittorio Loreto
author_sort Giordano De Marzo
collection DOAJ
description Recommender systems are vital for shaping user online experiences. While some believe they may limit new content exploration and promote opinion polarization, a systematic analysis is still lacking. In this paper we present a model that explores the influence of recommender systems on novel content discovery. Surprisingly, analytical and numerical findings reveal that these techniques can enhance novelty discovery rates. Also, distinct algorithms with similar discovery rates yield different outcomes, with the matrix factorization algorithm producing opinion polarization. Our approach shed light on the interplay between algorithmic recommendations and novelties discovery, offering a framework to enhance recommendation techniques beyond accuracy metrics.
format Article
id doaj-art-dbed2f9f44a14ac596440fdb1de82afb
institution OA Journals
issn 2632-072X
language English
publishDate 2024-01-01
publisher IOP Publishing
record_format Article
series Journal of Physics: Complexity
spelling doaj-art-dbed2f9f44a14ac596440fdb1de82afb2025-08-20T02:34:39ZengIOP PublishingJournal of Physics: Complexity2632-072X2024-01-015404500810.1088/2632-072X/ad9cddRecommender systems may enhance the discovery of noveltiesGiordano De Marzo0https://orcid.org/0000-0002-3127-5336Pietro Gravino1https://orcid.org/0000-0002-0937-8830Vittorio Loreto2University of Konstanz , Universitaetstrasse 10, 78457 Konstanz, Germany; Sony Computer Science Laboratories Paris , 6, Rue Amyot, 75005 Paris, France; Centro Ricerche Enrico Fermi , Piazza del Viminale, 1, 00184 Rome, Italy; Complexity Science Hub Vienna , Josefstaedter Strasse 39, 1080 Vienna, AustriaSony Computer Science Laboratories Paris , 6, Rue Amyot, 75005 Paris, France; Sony Computer Science Laboratories Rome , Joint Initiative CREF-SONY, Piazza del Viminale, 1, 00184 Rome, Italy; Centro Ricerche Enrico Fermi , Piazza del Viminale, 1, 00184 Rome, ItalySony Computer Science Laboratories Rome , Joint Initiative CREF-SONY, Piazza del Viminale, 1, 00184 Rome, Italy; Centro Ricerche Enrico Fermi , Piazza del Viminale, 1, 00184 Rome, Italy; Complexity Science Hub Vienna , Josefstaedter Strasse 39, 1080 Vienna, Austria; Sapienza University of Rome , P.le A. Moro, 2, 00185 Rome, ItalyRecommender systems are vital for shaping user online experiences. While some believe they may limit new content exploration and promote opinion polarization, a systematic analysis is still lacking. In this paper we present a model that explores the influence of recommender systems on novel content discovery. Surprisingly, analytical and numerical findings reveal that these techniques can enhance novelty discovery rates. Also, distinct algorithms with similar discovery rates yield different outcomes, with the matrix factorization algorithm producing opinion polarization. Our approach shed light on the interplay between algorithmic recommendations and novelties discovery, offering a framework to enhance recommendation techniques beyond accuracy metrics.https://doi.org/10.1088/2632-072X/ad9cddHeaps’ lawrecommendation algorithmsopinion polarizationurn models
spellingShingle Giordano De Marzo
Pietro Gravino
Vittorio Loreto
Recommender systems may enhance the discovery of novelties
Journal of Physics: Complexity
Heaps’ law
recommendation algorithms
opinion polarization
urn models
title Recommender systems may enhance the discovery of novelties
title_full Recommender systems may enhance the discovery of novelties
title_fullStr Recommender systems may enhance the discovery of novelties
title_full_unstemmed Recommender systems may enhance the discovery of novelties
title_short Recommender systems may enhance the discovery of novelties
title_sort recommender systems may enhance the discovery of novelties
topic Heaps’ law
recommendation algorithms
opinion polarization
urn models
url https://doi.org/10.1088/2632-072X/ad9cdd
work_keys_str_mv AT giordanodemarzo recommendersystemsmayenhancethediscoveryofnovelties
AT pietrogravino recommendersystemsmayenhancethediscoveryofnovelties
AT vittorioloreto recommendersystemsmayenhancethediscoveryofnovelties