SODAS Data Discussion w/ Gregory Eady & Mette Foss Andersen
Copenhagen Center for Social Data Science (SODAS), is pleased to announce that we are continuing with SODAS Data Discussions this fall.
SODAS aspirers to be a resource for all students and researchers at the Faculty of Social Sciences. We therefor invite researchers across the faculty to present ongoing research projects, project applications or just a loose idea that relates to the subject of social data science.
Every month two researchers will present their work. The rules are simple: short research presentations of ten minutes are followed by twenty minutes of debate. No papers will be circulated beforehand, and the presentations cannot be longer than five slides.
Assistant Professor at Department of Political Science, Gregory Eady will present his work followed by Mette Foss Andersen, who is a MSc student at the London School of Economics. Gregory Eady's substantive research agenda focuses on political behavior on social media, and his methodological work on developing quantitative methods and software for analyzing social media and public opinion survey data. Mette Foss Andersen is a Sociologist from the University of Copenhagen with 3 years of working experience in analyzing education and crime. Currently MSc Social Research student at the London School of Economics and Political Science. Interested in Quantitative Text Analysis, Big Data, and Social Network analysis.
Gregory Eady: Political Information Sharing and Ideological Polarization on Social Media
What explains the online information-sharing behavior of politicians and ordinary citizens? This article examines the sharing behavior of politicians and ordinary users by mapping the ideological foundation of political information shared on social media. As data, we use the near-universal currency of online political information exchange: URLs (i.e. web links). First, we introduce a new method (and statistical software) to unify the measurement of the political ideology, using social media sharing data to estimate the ideology of (1) politicians, (2) users, and (3) the news content that they share online. Second, we show empirically that legislators with more ideologically extreme voting records, and those who represent less competitive districts are more likely to share politically polarizing news. Third, we show however that it is ordinary users, not politicians, who share the most ideologically extreme content and contribute most to the polarized online news-sharing ecosystem. Our approach opens up many avenues for research into the communication strategies of legislators, citizens, and other actors who seek to influence political behavior and sway public opinion by sharing political information online.
Mette Foss Andersen: ISIS-activity on Twitter. A social network approach on how radical Islamistic propaganda is spread on the platform
The terrorist-organisation ISIS has over the last years re-structured to a less centralised institution, encouraging individuals to carry out attacks on their own. The primary foundation for recruitment is different social media platforms and research has shown that the organisation especially uses Twitter to broadcast its messages and recruit new fighters. This study aims to identify ISIS-activity on Twitter in the last weeks of ISIS’ self-promoted caliphate (13th of February to the 5th of March 2019) by the use of Machine Learning. The study also aims to conduct a Social Network Analysis on how the network is organised on Twitter and how ISIS-propaganda is spread on the platform. The corpus consists of 5,4 Mio tweets downloaded in the period, and 50.000 tweets from a crowd-sourcing initiative by the activist-organisation Anonymous who in 2014 asked volunteers with expertise in Arabic to report ISIS-activity on Twitter.
The SODAS Data Discussion will take place at SODAS in building 1, 2nd floor, room 26 (1.2.26) of the CSS Campus, University of Copenhagen, from 11.00 am to 12.00 noon.
If you have questions or want to know more, please write Sophie Smitt Sindrup Grønning at email@example.com.