EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Cracking double-blind review: Authorship attribution with deep learning

Leonard Bauersfeld iD, Angel Romero iD, Manasi Muglikar, Davide Scaramuzza

PLOS ONE · 30.06.2023 · 18 (6) · e0287611

DOI: 10.1371/journal.pone.0287611 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS ONE, online erschienen am 30.06.2023. Verfasst von Leonard Bauersfeld und 3 weiteren Autor:innen. Beteiligte Einrichtung: Robotics and Perception Group, University of Zurich, Zurich, Switzerland. Hauptthemen laut MEDLINE: Authorship, Deep Learning. Die Arbeit wurde bisher 17-mal zitiert (Crossref) und nennt 39 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Centre of Competence in Research (NCCR) Robotics through the Swiss National Science Foundation, European Research Council.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Double-blind peer review is considered a pillar of academic research because it is perceived to ensure a fair, unbiased, and fact-centered scientific discussion. Yet, experienced researchers can often correctly guess from which research group an anonymous submission originates, biasing the peer-review process. In this work, we present a transformer-based, neural-network architecture that only uses the text content and the author names in the bibliography to attribute an anonymous manuscript to an author. To train and evaluate our method, we created the largest authorship-identification dataset to date. It leverages all research papers publicly available on arXiv amounting to over 2 million manuscripts. In arXiv-subsets with up to 2,000 different authors, our method achieves an unprecedented authorship attribution accuracy, where up to 73% of papers are attributed correctly. We present a scaling analysis to highlight the applicability of the proposed method to even larger datasets when sufficient compute capabilities are more widely available to the academic community. Furthermore, we analyze the attribution accuracy in settings where the goal is to identify all authors of an anonymous manuscript. Thanks to our method, we are not only able to predict the author of an anonymous work but we also provide empirical evidence of the key aspects that make a paper attributable. We have open-sourced the necessary tools to reproduce our experiments.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

AuthorshipDeep LearningDouble-Blind MethodElectric Power SuppliesNeural Networks, Computer

Autor:innen und Institutionen

  • Robotics and Perception Group, University of Zurich, Zurich, Switzerland.

ORCID-Profile: Leonard Bauersfeld, Angel Romero

Förderung

  • National Centre of Competence in Research (NCCR) Robotics through the Swiss National Science Foundation
  • European Research Council

Zitieren

APA

Bauersfeld, L., Romero, A., Muglikar, M., & Scaramuzza, D. (2023). Cracking double-blind review: Authorship attribution with deep learning. PLOS ONE, 18(6), e0287611. https://doi.org/10.1371/journal.pone.0287611

Vancouver

Bauersfeld L, Romero A, Muglikar M, Scaramuzza D. Cracking double-blind review: Authorship attribution with deep learning. PLOS ONE. 2023;18(6):e0287611. doi:10.1371/journal.pone.0287611

BibTeX
@article{Bauersfeld2023,
  author = {Bauersfeld, Leonard and Romero, Angel and Muglikar, Manasi and Scaramuzza, Davide},
  title = {Cracking double-blind review: Authorship attribution with deep learning},
  journal = {PLOS ONE},
  year = {2023},
  volume = {18},
  number = {6},
  pages = {e0287611},
  doi = {10.1371/journal.pone.0287611}
}
Kostenlos starten →