@article{wagner2024_95383,
  title = {BibDedupe : An Open-Source Python Library for Bibliographic Record Deduplication},
  author = {Wagner, Gerit},
  year = {2024},
  journal = {The journal of open source software : a developer friendly journal for research software packages},
  volume = {9},
  number = {97, 6318},
  pages = {1-6},
  publisher = {The Open Journal},
  issn = {2475-9066},
  doi = {10.21105/joss.06318},
  url = {https://fis.uni-bamberg.de/handle/uniba/95383},
  language = {eng},
  abstract = {BibDedupe is a Python library developed for bibliographic record deduplication in meta-analysis and research synthesis. It is constructed with a focus on four requirements: (1) Zero false positives: The primary objective is to prevent incorrectly merging distinct entries. This focus on zero false positives is crucial to ensure trustworthiness and prevent biased conclusions in the analysis. (2) Reproducibility: BibDedupe implements fixed rules to produce consistent results, in line with the scientific standard of reproducibility. (3) Efficiency: The library is also tuned for low false-negative rates and rapid processing, to ensure scalability of the duplicate identification process. (4) Continuous evaluation and improvement: It is continuously evaluated on over 160,000 records from 10 datasets to ensure its effectiveness, especially in follow-up refinements. Unlike general-purpose deduplication tools, BibDedupe is specifically designed for the unique requirements of bibliographic data in meta-analysis and research synthesis. In this context, BibDedupe aims to provide a Python library that improves the effectiveness and efficiency of duplicate identification, potentially benefitting review papers across scientific disciplines.},
  keywords = {BibDedupe}
}
