Estimating Ideological Scores of Facebook Pages: An Empirical Study in Taiwan
Journal
The Computer Journal
Journal Volume
60
Journal Issue
11
Pages
2908-2917
Date Issued
2017
Author(s)
Abstract
With the emergence of social media sites such as Twitter and Facebook, channels have opened for citizens to publish an increasing and varied amount of personalized political information. In addition, social media has enabled users to broaden their political knowledge base through online interactions with individuals or groups. This study examines the ideological score of >0.2 million Facebook pages in Taiwan, where politics has long been polarized between the two major parties the Kuomintang (KMT) and the Democratic Progressive Party (DPP). This paper first measures users ideological scores along a Pro-KMT and Pro-DPP spectrum on the basis of their endorsements of political celebrities’ Facebook pages. Second, due to the one-dimensional polarization in Taiwanese politics, we assume that a user’s ideological position may lead them to endorse other Facebook pages that publish and share similar ideological content. Finally, based on this assumption, we estimate the ideological scores of the collected Facebook pages. Our results do not only present a political ideology estimation of pages with different perspectives (popularity, politicalness and category), they also propose applications of identifying potential political and conflicting/sarcastic pages.
Type
journal article