@inbook{1895f4384c824efaa206caf104a065e4,
title = "Capturing Contentiousness: Constructing the Contentious Terms in Context Corpus",
abstract = "Recent initiatives by cultural heritage institutions in addressing outdated and offensive language used in their collections demonstrate the need for further understanding into when terms are problematic or contentious.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.",
author = "Ryan Brate and Andrei Nesterov and Valentin Vogelmann and {van Ossenbruggen}, Jacco and Laura Hollink and {van Erp}, Marieke",
year = "2021",
month = dec,
doi = "10.1145/3460210.3493553",
language = "English",
series = "ACM Digital Library ",
publisher = "Association for Computing Machinery (ACM)",
pages = "17--24",
booktitle = "K-CAP '21",
address = "United States",
}