Capturing Contentiousness

Abstract

Recent initiatives by cultural heritage institutions in addressing outdated and offensive language used in their collections demonstrate the need for further understanding into when terms are problematic or contentious. This paper presents an annotated dataset of 2,715 unique samples of terms in context, drawn from a historical newspaper archive, collating 21,800 annotations of contentiousness from expert and crowd workers.We describe the contents of the corpus by analysing inter-rater agreement and differences between experts and crowd workers. In addition, we demonstrate the potential of the corpus for automated detection of contentiousness. We show that a simple classifier applied to the embedding representation of a target word provides a better than baseline performance in predicting contentiousness. We find that the term itself and the context play a role in whether a term is considered contentious. CCS CONCEPTS• Information systems → Digital libraries and archives; • Computing methodologies → Knowledge representation and reasoning.

A Knowledge Graph of Contentious Terminology for Inclusive Representation of Cultural Heritage

“…The development of a knowledge graph in this paper extends our previous work, in which we constructed a crowdsource-annotated corpus of contentious terms in contexts taken from historical newspapers [5]. The corpus was used for machine-learning based detection of contentiousness.…”

“…For example, institutions provide explanations about inappropriate terminology in content warnings accompanying online collections 4 or publish general statements on their websites. 5 There is expert knowledge about problematic terminology that GLAM and other actors have produced, however, this knowledge is often detached from digital collections [18]. While object descriptions in collections are structured and often interconnected in knowledge organisation systems (KOS) used by heritage institutions, the domain expertise and discussions about problematic words in these collections exist in separate publications in different formats.…”

“…A content warning in the Europeana gallery "Black people in European art": https://www.europeana.eu/en/galleries/black-people-in-european-art. Accessed on 10.12.20225 The Getty Research Institute "Anti-Racist Statement": https://www.getty.edu/ research/institute/antiracist_statement.html. Accessed on 10.12.20226 For example, the image entitled "slave from "[Across Africa, etc.…”