% IMPORTANT: The following is UTF-8 encoded. This means that in the presence
% of non-ASCII characters, it will not work with BibTeX 0.99 or older.
% Instead, you should use an up-to-date BibTeX implementation like “bibtex8” or
% “biber”.
@ARTICLE{Stanzel:908302,
author = {Stanzel, Franziska and Barbers, Irene and Pollack, Philipp
and Lindstrot, Barbara},
title = {{B}ig {S}cholarly {D}ata im {O}pen {A}ccess {M}onitor: ein
{W}erkstattbericht},
journal = {LIBREAS. Library ideas},
volume = {41},
issn = {1860-7950},
address = {Berlin},
publisher = {Institut für Bibliotheks- und Informationswissenschaft
der Humboldt Universität zu Berlin},
reportid = {FZJ-2022-02522},
pages = {20 pages},
year = {2022},
abstract = {In the light of the Open Access transformation, the
analysis of large amounts of data is increasingly important
for libraries, whereas the number of scholarly publications
is constantly growing. Large amounts of data must first be
made usable before any substantiated analysis can be made,
e.g. regarding institution-related publication outputs. This
is where the Open Access Monitor (OAM) comes in, which acts
as an interface for merging data from various source systems
such as Unpaywall, Dimensions, Web of Science and Scopus.
For this purpose, the OAM is structurally divided into three
parts: the backend hosts the data, which can be queried via
the API, and is presented and visualized in the frontend.
All data, coming from various source systems, must be
homogenized in order to realize complete data sets without
creating duplicates. Journal titles or institution names
have to be standardized to allow assigning the original
entries from the source systems to the corresponding data
records in the OAM. In the case of institution names, these
are enriched with persistent identifiers. Given the way the
data is organized in some of the source databases, the
institution names cannot be mapped directly to organization
identifiers (ROR-IDs) in some cases. Therefore, the raw
forms of the author’s affiliation information are used in
the mapping process. Affiliation mapping is an extensive and
complex task, since the data provided are often ambiguous
and at the same time a clear distinction of institutions,
especially in the case of university hospitals, requires
intellectual processing. The highly complex process of
generating a uniform data set from a multitude of data
sources will be demonstrated, with a special focus on the
normalization processes as well as the assignment of Open
Access categories. Metadata quality remains a constant
challenge, as does the issue of availability and
sustainability of the connected source systems. The use and
integration of open data sources is generally desirable –
it would be in line with the OAM’s goal of unrestricted
(re-) usability of the OAM data. The pros and cons of using
non-commercial databases are discussed using OpenAlex as an
example.},
keywords = {Publikationsdaten (Other) / Anwendung (Other) /
wissenschaftliches Publizieren (Other) / Open Access (Other)
/ Monitoring (Other) / open access monitoring (Other) /
publication data (Other) / application (Other) / scholarly
publishing (Other) / scholarly communication (Other)},
cin = {ZB},
ddc = {020},
cid = {I:(DE-Juel1)ZB-20090406},
pnm = {899 - ohne Topic (POF4-899) / OAM - Open Access Monitoring
– OAM (16OAMO001)},
pid = {G:(DE-HGF)POF4-899 / G:(DE-HGF)16OAMO001},
typ = {PUB:(DE-HGF)16},
doi = {10.18452/24797},
url = {https://juser.fz-juelich.de/record/908302},
}