Details
| Original language | English |
|---|---|
| Title of host publication | Proceedings of the 18th ACM Conference on Recommender Systems |
| Subtitle of host publication | RecSys 2024 |
| Pages | 1062-1066 |
| Number of pages | 5 |
| ISBN (electronic) | 9798400705052 |
| Publication status | Published - 8 Oct 2024 |
| Event | 18th ACM Conference on Recommender Systems, RecSys 2024 - Bari, Italy Duration: 14 Oct 2024 → 18 Oct 2024 |
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.
Keywords
- Adversarial attack, Data poisoning, Journal recommendation, Scientific publishing
ASJC Scopus subject areas
- Computer Science(all)
- Computer Science Applications
- Computer Science(all)
- Information Systems
- Computer Science(all)
- Software
- Engineering(all)
- Control and Systems Engineering
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
Proceedings of the 18th ACM Conference on Recommender Systems: RecSys 2024. 2024. p. 1062-1066.
Research output: Chapter in book/report/conference proceeding › Conference contribution › Research › peer review
}
TY - GEN
T1 - Can Editorial Decisions Impair Journal Recommendations?
T2 - 18th ACM Conference on Recommender Systems, RecSys 2024
AU - Entrup, Elias
AU - Ewerth, Ralph
AU - Hoppe, Anett
N1 - Publisher Copyright: © 2024 Copyright held by the owner/author(s).
PY - 2024/10/8
Y1 - 2024/10/8
N2 - 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.
AB - 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.
KW - Adversarial attack
KW - Data poisoning
KW - Journal recommendation
KW - Scientific publishing
UR - http://www.scopus.com/inward/record.url?scp=85210476990&partnerID=8YFLogxK
U2 - 10.1145/3640457.3688194
DO - 10.1145/3640457.3688194
M3 - Conference contribution
AN - SCOPUS:85210476990
SP - 1062
EP - 1066
BT - Proceedings of the 18th ACM Conference on Recommender Systems
Y2 - 14 October 2024 through 18 October 2024
ER -