• Corpus ID: 235795746

Designing Recommender Systems to Depolarize

  title={Designing Recommender Systems to Depolarize},
  author={Jonathan Stray},
  • J. Stray
  • Published 11 July 2021
  • Computer Science
  • ArXiv
Polarization is implicated in the erosion of democracy and the progression to violence, which makes the polarization properties of large algorithmic content selection systems (recommender systems) a matter of concern for peace and security. While algorithmdriven social media does not seem to be a primary driver of polarization at the country level, it could be a useful intervention point in polarized societies. This paper examines algorithmic depolarization interventions with the goal of… 
1 Citations
Estimating and Penalizing Preference Shift in Recommender Systems
This work advocate for estimating the preference shifts that would be induced by recommender system policies, and explicitly characterizing what unwanted shifts are and assessing before deployment whether such policies will produce them, and shows that recommender systems that optimize for staying in the trust region avoid manipulative behaviors, while still generating engagement.


Exposure diversity as a design principle for recommender systems
Suggestions for design principles are made and the potential and possible limits of ‘diversity sensitive design’ are explored, to break potential ‘filter bubbles’ rather than create them.
Do not blame it on the algorithm: an empirical assessment of multiple recommender systems and their impact on content diversity
It is found that all of the recommendation logics under study proved to lead to a rather diverse set of recommendations that are on par with human editors and that basing recommendations on user histories can substantially increase topic diversity within a recommendation set.
The Unified Framework of Media Diversity: A Systematic Literature Review
Abstract How to study media diversity has become a major concern in today’s media landscape. Many expect that algorithmic filtering and a shift of audiences from legacy media to new intermediaries
Breaking the filter bubble: democracy and design
It is argued that democracy itself is a contested concept and points to a variety of norms, so designers of diversity enhancing tools must thus be exposed to diverse conceptions of democracy.
On the Democratic Role of News Recommenders
Abstract Are algorithmic news recommenders a threat to the democratic role of the media? Or are they an opportunity, and, if so, how would news recommenders need to be designed to advance values and
Aligning AI Optimization to Community Well-Being
  • J. Stray
  • Medicine, Computer Science
    International journal of community well-being
  • 2020
This paper investigates incorporating community well-being metrics into the objectives of optimization algorithms and the teams that build them. It documents two cases where a large platform appears
Algorithmic Extremism: Examining YouTube's Rabbit Hole of Radicalization
YouTube's recommendation algorithm is shown to favor mainstream media and cable news content over independent YouTube channels with slant towards left-leaning or politically neutral channels, suggesting that it fails to promote inflammatory or radicalized content.
Hegemony in Social Media and the effect of recommendations
A new model featuring a mild version of homophily and two well-known popularity dynamics is introduced, showing this is all that is needed to create hegemony: a single viewpoint not only receives undue attention, but it also captures all the attention given to “top trending” items.
Evaluating the scale, growth, and origins of right-wing echo chambers on YouTube
It is found that political news content accounts for a relatively small fraction (11%) of consumption on YouTube, and is dominated by mainstream and largely centrist sources, however, there is evidence for a small but growing "echo chamber" of far-right content consumption.
Transformations through Polarizations and Global Threats to Democracy
This volume collects and analyzes eleven country case studies of polarized polities that are, or had been, electoral democracies, identifying the common and differing causal mechanisms that lead to