UM Data Science Research Seminar

The UM Data Science Research Seminar Series are monthly sessions organized by the Institute of Data Science, in collaboration with different departments across UM. The aim of these sessions is to bring together scientists from all over Maastricht University to discuss breakthroughs and research topics related to Data Science. This seminar is organized in collaboration with the Faculty of Arts ands Social Sciences (FASoS).

N.B.: All events are in-person and free of charge. We also offer participants a FREE lunch.

Schedule

Lecture: 12:00 - 12:45 Q&A: 12:45 - 13:00

Speaker: Eliyahu Sapir

Title: "A data-driven, a-posteriori, three-step method for identifying media frames: Reassessing the Brexit Referendum media discourse"

Abstract: In this paper, I take a data-driven approach to classifying the UK print newspaper coverage of the Brexit referendum run-up. While analyzing frames employed by the media in its coverage of a given topic is a widely used method in the social sciences, it is mostly theory-driven and unable to extract new frames from data corpora. Taking a data-driven approach, I employ Structural Topic Models to identify distinct topics covered by the media, and cluster them by their semantic proximity into media frames. The findings replicate previously identified frames and add additional ones, focusing on leading political figures from the Conservative, Labour and UKIP parties, the Brexit campaign and the specific issue-frames discussed by the media, first-and-foremost the economy, the Trade Deal, the Irish border, Scotland's independence, migration and Turkey's EU membership. These frames were next ordered by their importance in the news media discourse and regressed against outlets' positions, to compose the specific media frames combination employed by each of the contesting camps.