Lena Mangold | Doctorante
I am a PhD student in the Computational Social Science Team lead by Camille Roth, at Centre Marc Bloch (Berlin). In the context of the ERC socsemics project, my research focuses on the mathematical description and categorisation of socio-semantic clusters in online public spaces: subgroups of users not only segregated from the wider conversation in terms of social interaction but also separated from (and less exposed to) opinions and content outside of their group.
I first began using computational methods in the context of studying online debates in the spring of 2016, while I was studying for an MSc in Mathematical Modelling and Scientific Computing at the University of Oxford. It was a time in which the public debate in the United Kingdom was revolving around the polarising issue of the EU referendum – a topic that motivated me to venture into the field of computational social science in the broader sense, and to study online conversations, their potential fragmentation and resulting polarisation more specifically. As part of my thesis, I used methods from complex networks, information theory and natural language processing (amongst others) to analyse tweets surrounding the Brexit debate and to investigate the interplay between isolated social communities of users and semantic categories identified from text data.
More recently, I spent a number of years working within a computational social science context outside of academia, first as a data scientist for the UK Labour Party and later for a socially focused start-up in Colombia.
Sujet de recherche
As a PhD student under the supervision of Camille Roth, I will be working on the mathematical description and categorisation of socio-semantic clusters in online public spaces. The overarching aim of my PhD project is to work towards a typology of such clusters, to contribute to the understanding of the circumstances under which segregated, semantically reinforcing groups of people split off from wider online conversations. Broadly, I will model the dynamics in online debates as complex networks and incorporate the semantic dimension of the debates by using methods from the field of natural language processing. I intend to study the internal structure of socio-semantic clusters, conduct a comparative study of clusters in different contexts on a meta-level, and examine the micro-level dynamics at play as part of the emergence of such clusters.
Institution de la thèse
Directeur de thèse