Giulia Occhini

Photo of: Giulia Occhini


Doctoral Student

Cohort year


Partner Institution


Giulia is a doctoral student registered at the faculty of Science within the University of Bristol. Prior to joining The Alan Turing Institute, she obtained an MPhil in Linguistics at Leiden University and a joint BA in Modern and Classical Languages and Literatures at the University of Bologna and the University of Upper Alsace.

Giulia believes that methodological innovation is fundamental in order to make sure that the Humanities will remain relevant in the future, and she is particularly excited to be part of this innovation at the Turing. Her research interests lie principally within the fields of Digital Humanities and Natural Language Processing, which she explored during her time as a research assistant at the Leiden University Centre for Linguistics and the Royal Netherlands Institute for Southeast Asian and Caribbean Studies.

Research interests

Not only cities change, but they also change faster than the secondary data update pace (e.g. surveys). Moreover, cities change in myriads of ways, and therefore official sources of structured, secondary data may not be able to capture these changes. Giulia’s work at the Institute will use methodologies from Computational Linguistics in order to explore how the dynamics of the UK urban system can be detected - or even predicted - by mining internet content. These methods will be implemented with statistical modelling and spatial analysis in order to understand the spatiality of these processes, and will mainly utilise unstructured textual data from The Internet Archive.

The key aim of the project is to push the envelope of quantitative geography methodological tool-kit. While methods from computational linguistics have already been employed in Human Geography, their use has been limited to social media data thus far. Similarly, although business studies have used web mining and data from The Internet Archive before, their scope was rather limited and ignored the spatial signatures of these data.