What is the project about?
Understanding public discourse is essential for managing reactions to modern migration and integrating the newly arrived. In the wake of digitalization, much of the public sentiment, agenda setting, and political framing of societal developments has moved to social-media platforms, publicly-accessible newspaper repositories, and machine-readable archives of parliamentary speeches and party manifestos.
The project studies the discourse dynamics between politicians, media, and the public to understand meaning making, explore shifts in sentiment, and follow how collectively agreed narratives arise. The project combines research on migration and integration with the development of machine-learning applications for the sociological analysis of digitized text.
Project research questions
- How do the public discourses on immigration form and change over time?
What part do social media, traditional media, and political parties play and how do they interact with each other?
Is there a geographical variation in the content, meaning, and sentiment contained in social text?
How does opinion polarization occur online and how does misinformation spread?
How do discourse dynamics in local contexts (e.g. neighborhoods) interact with real-world events (e.g. crime) and outcomes (e.g. residential segregation)?
To answer these and related questions, the research team combines quantitative and qualitative methods for the computational analysis of text with temporal analyses for causal inference.
- Linköping University
- University of Lucerne
- Aalto University
- CNRS France
As many of the studied mechanisms defy disciplinary boundaries, the project approach is interdisciplinary and considers theoretical concepts from several social-science disciplines. The project brings together methodologically-oriented specialists of computational text analysis with social scientists attuned to the political process and the study of social dynamics to enable a novel combination of social-science theorizing and computational text analysis.
PublISHED ON 03 October 2019
UpDATED ON 09 April 2020