“Data Science behind the Guardian’s analysis of 100 years of MPs’ language on immigration”
4:00pm - 5:00pm /
Monday 27th April 2026
/ Venue: 502-FLEX-1 502 Teaching Hub, Mount Pleasant
Type: Lecture /
Category: Research
- school of the arts
- Suitable for: All welcome
- Admission: Free
- Event website
- Book now
Add this event to my calendar
Click on "Create a calendar file" and your browser will download a .ics file for this event.
Microsoft Outlook: Download the file, double-click it to open it in Outlook, then click on "Save & Close" to save it to your calendar. If that doesn't work go into Outlook, click on the File tab, then on Open & Export, then Open Calendar. Select your .ics file then click on "Save & Close".
Google Calendar: download the file, then go into your calendar. On the left where it says "Other calendars" click on the arrow icon and then click on Import calendar. Click on Browse and select the .ics file, then click on Import.
Apple Calendar: The file may open automatically with an option to save it to your calendar. If not, download the file, then you can either drag it to Calendar or import the file by going to File >Import > Import and choosing the .ics file.
The Language, Data and Society research centre (LANDS) is organising the following event to which you are welcome to join:
“Data Science behind the Guardian’s analysis of 100 years of MPs’ language on immigration”
Anna Vissens
(Head of Data Science Lead at Guardian News & Media)
Monday, 27 April 2026, 4pm-5pm
Room: 502-FLEX-1
Abstract: This project set out to analyse how political rhetoric around immigration in the UK Parliament has evolved over more than a century. While debates about immigration often focus on recent political developments, there has been little systematic analysis of how the tone and framing of parliamentary discourse have changed over time. Our objective was to provide an evidence-based understanding of these shifts by applying large-scale text analysis to parliamentary speeches delivered between 1919 and 2025. To achieve this, we developed a custom sentiment classification model designed to distinguish sentiment specifically directed toward immigration from general emotionally charged language. The project also explored the use of Large Language Models (LLMs) as auxiliary annotators to support the labelling of training data, helping to expand the dataset while maintaining quality through validation processes. By combining computational linguistics, machine learning and data journalism, the project demonstrates how advanced analytical methods can be used to study political language at scale and provide new insights into long-term trends in public discourse.
About the speaker: Anna Vissens (Data Science Lead, the Guardian, London, UK) is a physicist by trade but has spent nearly all her career in media, first as a journalist, and then as a data scientist. Anna leads a team of data scientists at the UK-based Guardian News and Media. Previously she worked at the BBC where in 2007 she received an award in recognition of success in building and engaging new audiences. Anna teaches different modules including AI ethics at LSE's annual AI Academy for small newsrooms. Her expertise spans across Natural Language Processing, Generative AI, recommender engines, audience segmentation, propensity models and more.
“Data Science behind the Guardian’s analysis of 100 years of MPs’ language on immigration”
Anna Vissens
(Head of Data Science Lead at Guardian News & Media)
Monday, 27 April 2026, 4pm-5pm
Room: 502-FLEX-1
Abstract: This project set out to analyse how political rhetoric around immigration in the UK Parliament has evolved over more than a century. While debates about immigration often focus on recent political developments, there has been little systematic analysis of how the tone and framing of parliamentary discourse have changed over time. Our objective was to provide an evidence-based understanding of these shifts by applying large-scale text analysis to parliamentary speeches delivered between 1919 and 2025. To achieve this, we developed a custom sentiment classification model designed to distinguish sentiment specifically directed toward immigration from general emotionally charged language. The project also explored the use of Large Language Models (LLMs) as auxiliary annotators to support the labelling of training data, helping to expand the dataset while maintaining quality through validation processes. By combining computational linguistics, machine learning and data journalism, the project demonstrates how advanced analytical methods can be used to study political language at scale and provide new insights into long-term trends in public discourse.
About the speaker: Anna Vissens (Data Science Lead, the Guardian, London, UK) is a physicist by trade but has spent nearly all her career in media, first as a journalist, and then as a data scientist. Anna leads a team of data scientists at the UK-based Guardian News and Media. Previously she worked at the BBC where in 2007 she received an award in recognition of success in building and engaging new audiences. Anna teaches different modules including AI ethics at LSE's annual AI Academy for small newsrooms. Her expertise spans across Natural Language Processing, Generative AI, recommender engines, audience segmentation, propensity models and more.