Projects

The Sahel has become the scene of unprecedented violence since 2012: a period that coincides with the advancement of new ICTs in the region. The role of digital connectivity is both a uniting and disruptive factor in this networked warfare. This project investigates this relationship where it will focus especially on information flows on social media as a legitimation of direct violence, i.e. Cultural Violence. This interdisciplinary study will rely on Natural Language Processing (NLP) and Social Network Analysis to understand the ‘workings’ of networked conflict interfering in the increasingly violent conflict in the Sahel (Africa) and beyond.

Project Page

As a PhD at the intersection of Digital Humanities & Korean studies, Aron is fascinated by how computer vision can enhance our understanding of Korea’s history. A critical aspect of this field involves the classification of printshops, which can aid in identifying the origin of printed documents from the colonial period. His project also utilizes optical character recognition (OCR) and object segmentation techniques to efficiently digitize and analyze collections of Korean texts and images. By using these computer vision methods, we can gain new insights into the evolution of Korean society, as well as the cultural and historical significance of various printshops and their products.

Matthew’s PhD project involves using computational methods and cartographic techniques to explore, visualise and analyse dialectal variation.

The primary focus of my project is to develop a tone distance metric which allows dialectologists to calculate dialect distances on the tonal level. In addition, the study will address dialectological questions such as “do dialect boundaries exist?” and “what are transition dialects like?” for both tonal and segmental levels, using Yue as a case study. To address these questions, the project look at 100+ dialects, and the findings are aimed to be non-language-specific, while the methods are aimed to be applicable cross-linguistically.

The language-specific component of my project is to revisit the classification of Yue dialects (internal classification within Yue, and the Yue-Pinghua dichotomy).

Personal website

Democracy is often said to be under the sway of “technocracy”: expert rule. Scientific institutions, experts and model have a tremendous influence on democratic decision-making, often at the cost of transparency and sovereignty. This research studies the rise of technocratic ways of thinking and the impact they have on democratic debate. It does so by mining and modelling millions of parliamentary debates from the twentieth century Dutch Lower House using NLP (Natural Language Processing) methods. Using language modelling, network analysis and argument mining, the research aims to uncover how expertise has become so important in politics.

Text alignment is a process of locating similar passages across different versions of documents. The degree to which two passages are similar is a matter open to debate; what similarity means in literature may be mathematically undefinable, due to the non-logical structure of human language. Buddhist texts often occur in multiple versions for various reasons, including document drafts, sectarian disagreements, and other phenomena of text transmission. While some alignments between texts seem obvious to human readers, there are also instances where alignment boundaries are ambiguous or unresolvable even for trained specialists. Using a custom genetic algorithm, I demonstrate some ways that these ambiguities can be transformed from obstacles into assets in the analysis of unknown texts.