Machine Learning

#148: Machine Learning the Facebook URLs Dataset to Study News Credibility, with Dr. Tom Paskhalis

 

Dr. Tom Paskhalis, Assistant Professor in Political and Data Science at Trinity College Dublin, shares his research on applying machine learning to the Facebook URLs Dataset from Social Science One. The project develops a model to label whether a news domain is credible or not based on Facebook interactions data. We discuss the Facebook URLs dataset, what types of machine learning techniques were applied to it, and how the model performed across the US and EU countries. 

#38: Algorithms, Social Media, and Society, with Dr. Thore Husfeldt

Dr. Thore Husfeldt, Associate Professor in computer science at IT University of Copenhagen and Professor in computer science and Lund University, is an algorithms theorist who joins the show to discuss the implications of algorithms for politics and society. We discuss how the algorithms of Facebook and Google have developed over time, how machine learning works, the upcoming European General Data Protection Regulation, and what all this means for democracy, politics, and society.

Check out the CAST IT podcast, hosted by Dr. Husfeldt.

Dr. Husfeldt’s talk on algorithms mentioned in the episode.