Abstract

Researchers’ task of finding a suitable open access journal for their work is becoming more and more complex: they have to comply with funder's conditions; their institutions hold various agreements with publishers; the number of journals is constantly growing (DOAJ 2018: 11.250 journals, 2021: >16.000 journals); so-called Predatory Publishers cause uncertainty. In order to reduce this complexity, TIB and SLUB Dresden, two major German research libraries, are developing B!SON, a web-based recommender for finding suitable Open Access journals. The tool calculates the similarity between a user's manuscript (title, abstract, references) and already published articles. Based on this similarity measure, B!SON will suggest Open Access journals in which similar articles have appeared. Researchers can use this information as guidance for their decision in which Open Access journal to publish. In addition, librarians can use B!SON for their publication support services and an API will allow the integration into existing library services. The results can be adapted to local conditions (e.g. price caps for institutional funding, Open Access agreements). The tool will use machine-learning techniques combined with a technical implementation of bibliometric algorithms proven in library practice. For this purpose, we will rely on the DOAJ article-level metadata corpus and the OpenCitations Index. We will analyze which article components give most reliable results in textual similarity analysis. Due to the ever-changing corpus of underlying data, the training process will be repeated regularly in the final tool. The information about journals (keywords, license, fees, etc.) will be provided by the DOAJ as well. We have built a community of researchers and librarians that we regularly consult in terms of specifications for the tool as well as – later in the project – acceptance and quality of its results. We plan to provide a beta version of B!SON in spring 2022. The project is funded by the German Federal Ministry of Education and Research. We present our schedule, facts and figures of the B!SON project and focus particularly on technical concepts of the project.

Highlights

  • 1.Machine-learning method for semantic similarity based on DOAJ's article metadata

  • B!SON "on the shoulders of giants“ – building upon and contributing to the ecosystem of open scientific infrastructures

Read more

Summary

Introduction

Anita Eppelin, https://orcid.org/0000-0003-0918-6297 Elias Entrup, https://orcid.org/0000-0002-7380-1189 Josephine Hartwig, https://orcid.org/0000-0002-5336-6853 Anett Hoppe, https://orcid.org/0000-0002-1452-9509 Munin Conference of Scholarly Publishing November 16-18, 2021

Results
Conclusion

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.