Practical Prompt Engineering for AI-Supported Metadata Processing in CRIS

Author(s)
Slovak Centre of Scientific and Technical Information (SCSTI)
FernUniversität in Hagen
Keywords

research information ...

current research info...

data quality

artificial intelligen...

subject classificatio...

SK CRIS

Issue Date
May 20, 2026
Publisher
euroCRIS
Type
Conference Paper
Abstract
Despite increasing demands on the quality of the research information held in CRIS systems, metadata workflows in many organizations remain highly manual and heterogeneous, relying heavily on individual interpretation and localized convention. Research in information science has long identified metadata quality as a persistent bottleneck in digital knowledge infrastructures . This challenge is exacerbated in the CRIS context, where metadata no longer serve merely descriptive purposes but underpin strategic decision-making, reporting to funders, international benchmarking, and institutional visibility. Manual assignment of scientific classifications, keywords, subject domains, or project categories is time-consuming, prone to inconsistency, and difficult to scale. Empirical studies repeatedly show that a lack of standardized procedures and varying interpretive practices contribute significantly to data heterogeneity and reduced metadata reliability. Simultaneously, most institutions lack dedicated AI teams or sufficient training data to develop custom machine-learning models capable of automating such tasks. Moreover, cross-institutional data harmonization and alignment with global ontologies remain largely unexplored, representing an opportunity to establish interoperable metadata networks at regional and international levels.
Description
12 slides.-- Presentation delivered within CRIS2026 session "AI for Metadata, Workflows, and Operational Research Information Management".-- Includes extended abstract
URI
https://dspacecris.eurocris.org/handle/11366/10292
File(s)
Thumbnail Image
Name

CRIS2026_paper-1_Zendulkova-Azeroual_Practical-Prompt-Engineering_extended-abstract.pdf

Description
Extended abstract
Size

179.82 KB

Format

Adobe PDF

Checksum (MD5)

52a904d2905c490cde7a9ef87db652a0

Thumbnail Image
Name

CRIS2026_Zendulkova-Azeroual_slides_AI-SKCRIS-metadata.pdf

Description
Presentation
Size

3.48 MB

Format

Adobe PDF

Checksum (MD5)

05995efa08878c68071c5326c53ec16c