Search

During the pandemic, the idea that digital adoption would revolutionise audience engagement became widespread in the museum sector. This paper explores whether this is true, utilising tools and debates from the digital humanities to analyse the online content and audiences of a representative sample of 315 museums in the UK.

Our work considers how new advances in pretrained text-to-text generation models might make named entity recognition more accurate, flexible, and streamlined for the digital humanist. We provide an example of how text-to-text generative models can identify mentions of characters, authors, and book names within Goodreads book reviews.

This presentation introduces our preliminary findings based on comparing the "classics" curated on Goodreads based in the U.S. and Douban based in China. The presented research is a case study for investigating the Anglophone vs. non-Anglophone online book reviewers' understandings of the classics.

We test the Aesthetic-Affective Potential (AAP), a word-embedding-based predictor for the perceived beauty of words. In a SentiArt context, AAP has also been shown to predict readers' liking of narrative passages. We investigate AAP and valence in the context of a large Dutch corpus of novels and their reviews.

In the last ten years, massive protests against the government and/or unfair elections took place in all three Eastern Slavic countries—Russia (2011/12), Ukraine (2014), and Belarus (2020). In 2022, protesters demonstrated against Russia's invasion of Ukraine. All these protests were mainly organized via social networks, were disseminated in independent media and countered by the official state-owned media. Thus, visual (self-)representations of the protest cultures must be recognized as an integral part of the protests proper. Our project unites close and distant viewing to assess how kaleidoscopic patterns of protest emerge from the constant recombination of specific visual symbols such as banners, flags, slogans, or people marching in the streets. Not only are we interested in a general description of visual and textual (self-)representations of protest in Eastern Europe but we also analyze the patterns of specific protest cultures to describe their symbolic repertoire. In order to achieve this, we build a corpus of visual and textual (self-)representations of protest. We then use deep learning to identify specific symbols in the corpus. These results are utilized to (1) visualize and analyze the differences between official and user-generated content, traditional and new media, and individual countries, and (2) to select specific images and video clips for a qualitative multimodal discourse analysis.

This contribution demonstrates a metadata-based approach to analyzing user networks of a German-language fanfiction website. Initially divided into clusters based on louvain modularity, the network is further modified to reveal the level of mutual interaction between reader-writers. The links are then categorized by various attributes, including genre and age restriction.

The Enriching Exhibition Scholarship project is developing and applying computational techniques to align socially-based textual and structured data, such as exhibition catalogues, newspapers and social media, making reconciliation easier and more effective. We use Linked Open Usable Data to describe and publish art-related knowledge.