Estimating ideology and polarization in European countries using Facebook data

Abstract

AbstractResearchers have studied political ideology and polarization in many different contexts since their effects are usually closely related to aspects and actions of individuals and societies. Hence, being able to estimate and measure the changes in political ideology and polarization is crucial for researchers, stakeholders, and the general public. In this paper, we model the ideology and polarization of 28 countries (the 27 EU member states plus the UK) using Facebook public posts from political parties’ Facebook pages. We collected a three-year dataset from 2019 to 2021 with information from 234 political parties’ Facebook pages and took advantage of the EU parliament elections of May 2019 to create our models. Our methodology works across 28 countries and benefits from being a low-cost running process that measures ideology and polarization at a high-resolution time scale. The results show our models are pretty accurate when validating them against 19 individual countries’ elections as ground truth. Moreover, to make our results available to the research community, stakeholders, and individuals interested in politics, the last contribution of our paper is a website including detailed information about the political parties in our dataset. It also includes the temporal evolution of our ideology and polarization estimations. Therefore, our work delivers a novel tool that uses Facebook public data to create country metrics useful for different purposes. To the best of our knowledge, there is no prior work in the literature offering a solution that measures the ideology and polarization of all EU + UK countries.