SODAS Data Discussion 17 December 2021
Copenhagen Center for Social Data Science (SODAS) aspirers to be a resource for all students and researchers at the Faculty of Social Sciences. We therefore 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.
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.
Author:
Peter Halkier Nicolajsen, Senior Data Scientist, LEGO
Title:
Effect of visible scalar feedback counts on user behavior in kids’ social media
Abstract:
Does the removal of visible ‘like’ counts align with theory in terms of its effect on behavior? This is investigated by monotoring differences in behavior between users of a kids’ social media experience, when visible like counts are removed for a share of the user base.
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
Author:
Charles de Dampierre, PhD student, Ecole Normale Supérieure, Paris and a data scientist at the Science-Po medialab. His research focuses on using the semantic approach of the web to describe and explain the different mental representations people have of a phenomenon online.
Title:
Mapping the anti-Semitic footprint on Youtube in France
Abstract:
The rise of social networks has opened up a new space for communication and debate, without borders and without limits, where racist and anti-Semitic comments are worryingly multiplying. Recent advances in Natural Language Processing now make it possible to study this type of phenomenon on a new scale. A study carried out by the Science Po medialab and published in the annual report of the French Human Rights commission on the fight against racism, anti-Semitism and xenophobia explored this subject. From a corpus of 628 French news channels on Youtube and nearly two million comments, the team trained an algorithm to recognise anti-Semitic speech in order to study the dynamics and distribution of antisemitism in the French online informational space. This exploratory approach poses many challenges that will be discussed during the meeting.
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
Authors:
Frederik Møller Henriksen, PhD & Jakob Bæk Kristensen, Postdoc, Roskilde University
Title:
Building large networks based on cross-platform link sharing for analysing online partisan communities
This event will take place on Zoom