Historical texts often contain terminology that reflects outdated or harmful social values. Identifying such contentious terms is essential for the Galleries, Libraries, Archives, and Museums (GLAM) community, but manual annotation requires cultural expertise and is difficult to scale. This study evaluates whether large language models (LLMs) can support this process by aligning with human judgments of contentiousness in historical Dutch corpora. Using the Dutch Contentious terms in Contexts Corpus (ConConCor), we formalize the task as context-dependent binary classification and compare two LLMs across multiple prompt configurations and evaluation scenarios. The models achieve near-human-level agreement on explicit cases but diverge when contextual or historical reasoning is required. Analysis of disagreement patterns shows that LLMs capture overtly harmful expressions yet tend to over-predict contentiousness for identity-related and colonial terms and under-predict for semantically shifted or figurative uses. These findings suggest that LLMs can serve as auxiliary annotators for sensitive-language detection in historical materials, provided that human oversight and contextual interpretation remain central to annotation workflows.

Web resources in linked open data (LOD) are comprehensible to humans through literal textual values attached to them, such as labels, notes, or comments. Word choices in literals may not always be neutral. When culturally stereotyping terminology is used in literals, they may appear as offensive to users in interfaces and propagate stereotypes to algorithms trained on them. We study how frequently and in which literals contentious terms about people and cultures occur in LOD and whether there are attempts to mark the usage of such terms. For our analysis, we reuse English and Dutch terms from a knowledge graph that provides opinions of experts from the cultural heritage domain about terms' contentiousness. We inspect occurrences of these terms in four widely used datasets: Wikidata, The Getty Art & Architecture Thesaurus, Princeton WordNet, and Open Dutch WordNet. Some terms are ambiguous and contentious only in particular senses. Applying word sense disambiguation, we generate a set of literals relevant to our analysis. We found that contentious terms frequently appear in descriptive and labelling literals, such as preferred labels that are usually displayed in interfaces and used for indexing. In some cases, LOD contributors mark contentious terms with words and phrases in literals (implicit markers) or properties linked to resources (explicit markers). However, such marking is rare and non-consistent in all datasets. Our quantitative and qualitative insights could be helpful in developing more systematic approaches to address the propagation of stereotypes via LOD.

The extent to which popularity bias is propagated by media recommender systems is a current topic within the community, as is the uneven propagation among users with varying interests for niche items. Recent work focused on exactly this topic, with movies being the domain of interest. Later on, two different research teams reproduced the methodology in the domains of music and books, respectively. The results across the different domains diverge. In this paper, we reproduce the three studies and identify four aspects that are relevant in investigating the differences in results: data, algorithms, division of users in groups and evaluation strategy. We run a set of experiments in which we measure general popularity bias propagation and unfair treatment of certain users with various combinations of these aspects. We conclude that all aspects account to some degree for the divergence in results, and should be carefully considered in future studies. Further, we find that the divergence in findings can be in large part attributed to the choice of evaluation strategy.

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.

Modeling user interests helps to improve system support or refine recommendations in Interactive Information Retrieval. The aim of this study is to identify user interests in different parts of an online collection and investigate the related search behavior. To do this, we propose to use the metadata of selected facets and clicked documents as features for clustering sessions identified in user logs. We evaluate the session clusters by measuring their stability over a six-month period.

With the growing abundance of unlabeled data in real-world tasks, researchers have to rely on the predictions given by black-boxed computational models. However, it is an often neglected fact that these models may be scoring high on accuracy for the wrong reasons. In this paper, we present a practical impact analysis of enabling model transparency by various presentation forms. For this purpose, we developed an environment that empowers non-computer scientists to become practicing data scientists in their own research field. We demonstrate the gradually increasing understanding of journalism historians through a real-world use case study on automatic genre classification of newspaper articles. This study is a first step towards trusted usage of machine learning pipelines in a responsible way.

Web usage mining has traditionally focused on the individual queries or query words leading to a web site or web page visit, mining patterns in such data. In our work, we aim to characterize websites in terms of the semantics of the queries that lead to them by linking queries to large knowledge bases on the Web. We demonstrate how to exploit such links for more effective pattern mining on query log data. We also show how such patterns can be used to qualitatively describe the differences between competing websites in the same domain and to quantitatively predict website abandonment.

Abstract Finding audiovisual material for reuse in new programs is an important activity for news producers, documentary makers, and other media professionals. Such professionals are typically served by an audiovisual broadcast archive. We report on a study of the transaction logs of one such archive. The analysis includes an investigation of commercial orders made by the media professionals and a characterization of sessions, queries, and the content of terms recorded in the logs. One of our key findings is that there is a strong demand for short pieces of audiovisual material in the archive. In addition, while searchers are generally able to quickly navigate to a usable audiovisual broadcast, it takes them longer to place an order when purchasing a subsection of a broadcast than when purchasing an entire broadcast. Another key finding is that queries predominantly consist of (parts of) broadcast titles and of proper names. Our observations imply that it may be beneficial to increase support for fine‐grained access to audiovisual material, for example, through manual segmentation or content‐based analysis.

It is common practice in audiovisual archives to disclose documents using metadata from a structured vocabulary or thesaurus. Many of these thesauri have limited or no structure. The objective of this paper is to find out whether retrieval of audiovisual resources from a collection indexed with an in-house thesaurus can be improved by enriching the thesaurus structure. We propose a method to add structure to a thesaurus by anchoring it to an external, semantically richer thesaurus. We investigate the added value of this enrichment for retrieval purposes. We first anchor the thesaurus to an external resource, WordNet. From this anchoring we infer relations between pairs of terms in the thesaurus that were previously unrelated. We employ the enriched thesaurus in a retrieval experiment on a TRECVID 2007 dataset. The results are promising: with simple techniques we are able to enrich a thesaurus in such a way that it adds to retrieval performance.

No abstract available.

In this paper, we propose an automatic video retrieval method based on high-level concept detectors. Research in video analysis has reached the point where over 100 concept detectors can be learned in a generic fashion, albeit with mixed performance. Such a set of detectors is very small still compared to ontologies aiming to capture the full vocabulary a user has. We aim to throw a bridge between the two fields by building a multimedia thesaurus, i.e., a set of machine learned concept detectors that is enriched with semantic descriptions and semantic structure obtained from WordNet. Given a multimodal user query, we identify three strategies to select a relevant detector from this thesaurus, namely: text matching, ontology querying, and semantic visual querying. We evaluate the methods against the automatic search task of the TRECVID 2005 video retrieval benchmark, using a news video archive of 85 h in combination with a thesaurus of 363 machine learned concept detectors. We assess the influence of thesaurus size on video search performance, evaluate and compare the multimodal selection strategies for concept detectors, and finally discuss their combined potential using oracle fusion. The set of queries in the TRECVID 2005 corpus is too small for us to be definite in our conclusions, but the results suggest promising new lines of research.

Semantic annotation of digital objects within large multimedia collections is a difficult and challenging task. We describe a method for semi-automatic annotation of images and apply it to and evaluate it on images of pancreatic cells. By comparing the performance of this approach in the pancreatic cell domain with previous results in the fuel cell domain, we aim to determine characteristics of a domain which indicate that the method will or will not work in that domain. We conclude by describing the types of images and domains in which we can expect satisfactory results with this approach.

To ensure access to growing video collections, annotation is becoming more and more important using background knowledge in the form of ontologies or thesauri is a way to facilitate annotation in a broad domain. Current ontologies are not suitable for (semi-) automatic annotation of visual resources as they contain little visual information about the concepts they describe. We investigate how an ontology that does contain visual information can facilitate annotation in a broad domain and identify requirements that a visual ontology has to meet. Based on these requirements, we create a visual ontology out of two existing knowledge corpora (WordNet and MPEG-7) by creating links between visual and general concepts. We test performance of the ontology on 40 shots of news video, and discuss the added value of each visual property.

In this presentation, we present a system for interactive search in video archives. In our view, interactive search is a four-step process composed of indexing, filtering, browsing, and ranking. We have experimentally verified, using 22 groups of two participants each, how users apply these steps in the interactive search and how well they perform.