Bias Tracker: Understanding sentiment in the run-up to the Italian elections

Douglas Arellanes, Sourcefabric Co-Founder
March 2, 2018

How might we use machine learning to identify articles that are true or not?  That question inspired TechCamp Reconnect Warsaw attendees Douglas Arellanes of Sourcefabric and Michelangelo ‘Ugo’ Barbara of Agi News Agency to create Bias Tracker, an open source tool that uses automated sentiment analysis to detect bias in online media.  With seed funding from the TechCamp program, Douglas and Ugo, in collaboration with the University of Urbino, recently launched a prototype for the Bias Tracker and tested it in the run-up to Italy’s March 2018 general election.  In this article, Douglas talks about Bias Tracker, how the team used it to successfully analyze sentiment in more than 57,000 Facebook posts from Italian media sources, and the tool’s broader potential to aid efforts to combat the spread of “fake news” and disinformation: