Can Editorial Decisions Impair Journal Recommendations?

Analysing the Impact of Journal Characteristics on Recommendation Systems

verfasst von: Elias Entrup, Ralph Ewerth, Anett Hoppe
Abstract: Recommendation services for journals help scientists choose appropriate publication venues for their research results. They often use a semantic matching process to compare e.g. an abstract against already published articles. As these services can guide a researcher’s decision, their fairness and neutrality are critical qualities. However, the impact of journal characteristics (such as the abstract length) on recommendations is understudied. In this paper, we investigate whether editorial journal characteristics can lead to biased rankings from recommendation services, i.e. if editorial choices can systematically lead to a better ranking of one’s own journal. The performed experiments show that longer abstracts or a higher number of articles per journal can boost the rank of a journal in the recommendations. We apply these insights to an active, open-source journal recommendation system. The adaptation of the algorithm leads to an increased accuracy for smaller journals.
Organisationseinheit(en): Forschungszentrum L3S
Externe Organisation(en): Technische Informationsbibliothek (TIB) Leibniz-Informationszentrum Technik und Naturwissenschaften und Universitätsbibliothek
Typ: Aufsatz in Konferenzband
Seiten: 1062-1066
Anzahl der Seiten: 5
Publikationsdatum: 08.10.2024
Publikationsstatus: Veröffentlicht
Peer-reviewed: Ja
ASJC Scopus Sachgebiete: Angewandte Informatik, Information systems, Software, Steuerungs- und Systemtechnik
Elektronische Version(en): https://doi.org/10.1145/3640457.3688194 (Zugang: Offen)

BibTeX

@inproceedings{25e4d96b6e1e4438a4b9a47ca8ba70a5,
title = "Can Editorial Decisions Impair Journal Recommendations?: Analysing the Impact of Journal Characteristics on Recommendation Systems",
abstract = "Recommendation services for journals help scientists choose appropriate publication venues for their research results. They often use a semantic matching process to compare e.g. an abstract against already published articles. As these services can guide a researcher{\textquoteright}s decision, their fairness and neutrality are critical qualities. However, the impact of journal characteristics (such as the abstract length) on recommendations is understudied. In this paper, we investigate whether editorial journal characteristics can lead to biased rankings from recommendation services, i.e. if editorial choices can systematically lead to a better ranking of one{\textquoteright}s own journal. The performed experiments show that longer abstracts or a higher number of articles per journal can boost the rank of a journal in the recommendations. We apply these insights to an active, open-source journal recommendation system. The adaptation of the algorithm leads to an increased accuracy for smaller journals.",
keywords = "Adversarial attack, Data poisoning, Journal recommendation, Scientific publishing",
author = "Elias Entrup and Ralph Ewerth and Anett Hoppe",
note = "Publisher Copyright: {\textcopyright} 2024 Copyright held by the owner/author(s).; 18th ACM Conference on Recommender Systems, RecSys 2024 ; Conference date: 14-10-2024 Through 18-10-2024",
year = "2024",
month = oct,
day = "8",
doi = "10.1145/3640457.3688194",
language = "English",
pages = "1062--1066",
booktitle = "Proceedings of the 18th ACM Conference on Recommender Systems",
publisher = "Association for Computing Machinery, Inc",
}