How do recommender systems learn political opinions? A semi-synthetic step-by-step experiment

• Tim Faverjon ,

  Contributed equally to this work with: Tim Faverjon, Jean-Philippe Cointet, Pedro Ramaciotti

  Roles Conceptualization, Formal analysis, Investigation, Methodology, Visualization, Writing – original draft, Writing – review & editing

  Affiliations médialab Sciences Po, Paris, France, Learning Planet Institute, Learning Transitions, CY Cergy Paris University, Paris, France

  ⨯
• Jean-Philippe Cointet ,

  Contributed equally to this work with: Tim Faverjon, Jean-Philippe Cointet, Pedro Ramaciotti

  Roles Data curation, Formal analysis, Methodology, Validation, Writing – review & editing

  Affiliation médialab Sciences Po, Paris, France

  ⨯
• Pedro Ramaciotti

  Contributed equally to this work with: Tim Faverjon, Jean-Philippe Cointet, Pedro Ramaciotti

  Roles Conceptualization, Data curation, Formal analysis, Funding acquisition, Investigation, Methodology, Project administration, Resources, Supervision, Validation, Visualization, Writing – original draft, Writing – review & editing

  * E-mail: pedro.ramaciotti-morales@cnrs.fr

  Affiliations médialab Sciences Po, Paris, France, Learning Planet Institute, Learning Transitions, CY Cergy Paris University, Paris, France, Complex Systems Institute of Paris Ile-de-France ISC-PIF CNRS, Paris, France

  https://orcid.org/0000-0002-3649-4503

  ⨯