Automated metadata annotation: What is and is not possible with machine learning

Ming Fang Wu, Hans Brandhorst, Maria Cristina Marinescu, Joaquim More Lopez, Margorie Hlava, Joseph Busch

Research output: Indexed journal article Articlepeer-review

6 Citations (Scopus)


Automated metadata annotation is only as good as training dataset, or rules that are available for the domain. It’s important to learn what type of data content a pre-trained machine learning algorithm has been trained on to understand its limitations and potential biases. Consider what type of content is readily available to train an algorithm—what’s popular and what’s available. However, scholarly and historical content is often not available in consumable, homogenized, and interoperable formats at the large volume that is required for machine learning. There are exceptions such as science and medicine, where large, well documented collections are available. This paper presents the current state of automated metadata annotation in cultural heritage and research data, discusses challenges identified from use cases, and proposes solutions.

Original languageEnglish
Pages (from-to)122-138
Number of pages17
JournalData Intelligence
Issue number1
Publication statusPublished - 1 Dec 2023
Externally publishedYes


  • Culture heritage
  • Metadata annotation
  • Metadata, Machine learning
  • Research data


Dive into the research topics of 'Automated metadata annotation: What is and is not possible with machine learning'. Together they form a unique fingerprint.

Cite this