Loading Events

« All Events

  • This event has passed.

Human vs machine: what can corpus linguistics contribute to our understanding of large collections of texts?

Keynote Speaker: Professor Sylvia Jaworska, Department of English Language and Applied Linguistics

A collaboration between Heritage & Creativity and Prosperity & Resilience on Wednesday 7 February 2024 from 14:00-15.30.

Location: Palmer 103 and Online

14.00 Welcome and introduction Dr Mara Olivia, Digital Humanities Champion

Professor Roberta Gilchrist, Research Dean, Heritage & Creativity

Professor Adrian Bell, Research Dean, Prosperity & Resilience

14.10 Keynote address: Human vs machine: what can corpus linguistics contribute to our understanding of large collections of texts? Professor Sylvia Jaworska
14.40 Roundtable Dr Jonathan Golub (Politics & International Relations): “Treating the text of EU legislative proposals as data”

Dr Rachel Foxley (History):A beginner’s project in textual analysis: political polarisation in the English Civil War”

Professor Mike Goodman (Geography & Environmental Science): “Analysing the texts of #CovidTwitter and getting students to de-normalise the world through frame analysis”

15.10 Q&A
15.30 What’s next for the Digital Humanities Community of Practice and Hub? and close. Dr Mara Olivia


In this talk, I will first outline key principles underlying the linguistically informed approach of corpus linguistics which has been adopted to study discourse in large collections of texts (corpora). I will focus in particular on the analytical tools of frequency, concordance, collocation and keyword and the software programme Sketch Engine to show the benefits of this approach to identify and examine discourse patterns and topics in large text corpora. Examples will include collaborative work conducted with researchers from HBS, SAGES and Pharmacy. The second part will compare the corpus approach with another popular method widely used in social sciences, that of topic modelling, which was developed in computer science. It will report on insights from a small quasi-experiment in which the two approaches were used to identify topics in a corpus of sustainability reports. The talk explores how the identified topics were similar and different and what this means for the analytical power of the two methods. I will conclude with a series of tentative observations regarding the benefits and limitations of each method and recommendations for researchers in choosing analytical technique to study large collections of texts available digitally.


Professor Sylvia Jaworska explores professional communication in (new) media, business and health settings focusing predominantly (but not exclusively) on the ways in which language and other semiotic choices are used to construct identities and perpetuate social stereotyping, biases and stigma. She examines discourse and communication using tools and techniques from corpus linguistics and discourse analysis as well as other quantitative and qualitative methods adopted in linguistics and social sciences including interviews, focus groups and surveys.

Dr Jonathan Golub is a political scientist using quantitative and qualitative methods to analyse decision making in the European Union. He is particularly interested in modelling the EU policymaking process and issues of institutional performance, such as the role of formal versus informal rules, the potential trade-off between efficiency and democratic legitimacy, and the distribution of power between Member States and supranational actors. His research interests also include modelling UN Security Council decision making, evaluating the effects of economic sanctions, studying the determinants of national and global environmental policy, and understanding judicial politics.

Dr Rachel Foxley’s work focuses on the history of political language and political thought, particularly in seventeenth-century England. Her PhD and first book were on the Levellers, and looked at the way in which this remarkably audacious network of activists and pamphleteers adapted and reworked the less radical thought of the parliamentarian cause which they had supported. Her more recent and current work focuses particularly on the writings of the English republican writers of the seventeenth century, including John Milton, James Harrington, Marchamont Nedham, Henry Neville, and Algernon Sidney. She is working on a book on their complex and perhaps conflicted treatments of the idea of democracy, and have published several shorter pieces on them. She has an abiding interest in the reception of classical ideas in early modern Europe, which is highly relevant to this project, and she is co-editing the Brill’s Companion to the Legacy of Greek Political Thought with David Carter and Elizabeth Sawyer. She is also interested in the gendered aspects of political texts and political thought, and hopes to focus on this more in future work.

Professor Mike Goodman is an interdisciplinary, critical human geographer focusing on the cultural politics of food, humanitarianism and the environment. Research topics have included fair trade networks, alternative food networks, the rise of celebrity politics in the context of food, climate change and global development and ways society is attempting to make life more just, liveable and care-full in the Anthropocene. He is particularly interested in conceptualising how these issues and connections are framed in the media in order to understand their social and geographical significance to building more sustainable societies, challenging existing structures of power and offering critical spaces for marginalised voices.

If you are not already a member, you are welcome to join the Digital Humanities Community of Practice via our MS Teams channel. (This link will take you to the Teams channel. If you are not already a member, you will be presented with a dialogue box that says ‘Join’. Click this to send a request, which will be approved if you are a member of the University of Reading. If you are already a member of the Team, this link just takes you directly to the ‘General’ channel.) or email the DH Champion, Dr Mara Oliva (m.oliva@reading.ac.uk)

Within the COP, you will be able to introduce yourself, share your research, and access information about funding opportunities, support, and events. Read more here.

Our events are open to all researchers, staff, and PGRs from any subject – we welcome interdisciplinary collaboration!


7 February
2:00 pm - 3:30 pm
Event Categories:
Event Tags:
, , ,


Palmer 103