Estimating ideology and polarization in European countries using Facebook data

Area of Science:

• Social Sciences
• Political Science
• Computational Social Science

Background:

• Political ideology and polarization significantly influence individual and societal actions.
• Accurate measurement of these phenomena is crucial for researchers, stakeholders, and the public.
• Existing methods may lack the scope or granularity to capture cross-country political dynamics.

Purpose of the Study:

• To develop and validate a novel methodology for modeling political ideology and polarization.
• To analyze these dynamics across 27 EU member states plus the UK.
• To create a publicly accessible resource for political data analysis.

Main Methods:

• Utilized a three-year dataset (2019-2021) of public Facebook posts from 234 political parties' pages.
• Leveraged the 2019 EU parliament elections for model calibration and validation.
• Developed a low-cost, high-resolution temporal analysis method applicable across multiple countries.

Main Results:

• Successfully modeled ideology and polarization for 28 countries (EU27 + UK).
• Validated model accuracy against 19 individual countries' election results.
• Achieved high-resolution temporal analysis of political shifts.

Conclusions:

• The study presents a novel, accurate, and cost-effective tool for measuring political ideology and polarization.
• A publicly available website offers temporal evolution data for political parties and countries.
• This work addresses a gap in the literature by providing comprehensive EU + UK political landscape metrics.