Do not blame it on the algorithm: an empirical assessment of multiple recommender systems and their impact on content diversity

  title={Do not blame it on the algorithm: an empirical assessment of multiple recommender systems and their impact on content diversity},
  author={Judith E. M{\"o}ller and Damian Trilling and Natali Helberger and Bram van Es},
  journal={Information, Communication \& Society},
  pages={959 - 977}
ABSTRACT In the debate about filter bubbles caused by algorithmic news recommendation, the conceptualization of the two core concepts in this debate, diversity and algorithms, has received little attention in social scientific research. This paper examines the effect of multiple recommender systems on different diversity dimensions. To this end, it maps different values that diversity can serve, and a respective set of criteria that characterizes a diverse information offer in this particular… 

A factual and perceptional framework for assessing diversity effects of online recommender systems

A framework for assessing different forms of diversity in online RS employs various recommendation algorithms and compares their impact using not just one but three different types of diversity measures, which helps explaining some of the contradictious findings from the previous literature.

SIREN: A Simulation Framework for Understanding the Effects of Recommender Systems in Online News Environments

It is argued that simulating the effects of recommender systems can help content providers to make more informed decisions when choosing algorithmic recommenders, and as such can help mitigate the aforementioned societal concerns.

One Recommender Fits All? An Exploration of User Satisfaction With Text-Based News Recommender Systems

The findings show that users prefer recommendations of the most similar articles, which are at the same time perceived as novel, but not necessarily unexpected, which will differ depending on personal characteristics such as formal education, the civic information norm, and the need for cognitive closure.

The Daily Me versus The Daily Others: How Do Recommendation Algorithms Change User Interests on Knowledge Sharing Platforms?

It is shown that compared with content-based filtering, social filtering algorithms are more likely to expose general users to content consumed by their followees who are more interested in niche topics than general users.

3bij3 – Developing a framework for researching recommender systems and their effects

3bij3 is developed, one of the first software solutions to conduct studies on effects of news recommender systems in a realistic setting, and gives researchers control over the recommendation system under study and creates a realistic environment for the participants.

bij 3 – Developing a framework for researching recommender systems and their effects

3bij3 gives researchers control over the recommendation system under study and creates a realistic environment for the participants, which integrates web scraping, different methods to compare and classify news articles, different recommender systems, a web interface for participants, gamification elements, and a user survey to enrich the behavioural measures obtained.

News Recommender Systems and News Diversity, Two of a Kind? A Case Study from a Small Media Market

Content recommender systems have become commonplace in all digital platforms, and they profoundly alter the media content presented to users. This also applies to news recommender systems (NRSs) used

Recommender systems and the amplification of extremist content

: Policymakers have recently expressed concerns over the role of recommendation algorithms and their role in forming “filter bubbles”. This is a particularly prescient concern in the context of

Building Human Values into Recommender Systems: An Interdisciplinary Synthesis

This paper collects a set of values that seem most relevant to recommender systems operating across different domains, then examines them from the perspectives of current industry practice, measurement, product design, and policy approaches.

A survey on knowledge-aware news recommender systems

This survey provides a comprehensive review of knowledge-aware news recommender systems and proposes a taxonomy that divides the models into three categories: neural methods, non-neural entity-centric methods, and non-Neural path-based methods.



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.

Diversity in recommender systems - A survey

An Algorithmic Diversity Diet?: Questioning Assumptions behind a Diversity Recommendation System for PSM

The design of a diversity diet system generates questions not just about editorial power, personal freedom and techno-paternalism, but also about the embedded politics of recommender systems as well as the human skills affiliated with PSM editorial work and the nature of PSM content.

Explaining the user experience of recommender systems

This paper proposes a framework that takes a user-centric approach to recommender system evaluation that links objective system aspects to objective user behavior through a series of perceptual and evaluative constructs (called subjective system aspects and experience, respectively).

Multiobjective Pareto-Efficient Approaches for Recommender Systems

The proposed Pareto-efficient approaches are effective in suggesting items that are likely to be simultaneously accurate, diverse, and novel and discussed scenarios where the system achieves high levels of diversity and novelty without compromising its accuracy.

Down the (White) Rabbit Hole: The Extreme Right and Online Recommender Systems

The evidence presented in this article supports a shift of the almost exclusive focus on users as content creators and protagonists in extremist cyberspaces to also consider online platform providers as important actors in these same spaces.

A survey of serendipity in recommender systems

Ways of Computing Diverse Collaborative Recommendations

This work devise and compare four different mechanisms for enhancing the diversity of the recommendations made by collaborative recommenders and finds that measuring the distance between products using Hamming Distance is more effective than using Inverse Pearson Correlation.

Exposure to ideologically diverse news and opinion on Facebook

Examination of the news that millions of Facebook users' peers shared, what information these users were presented with, and what they ultimately consumed found that friends shared substantially less cross-cutting news from sources aligned with an opposing ideology.

Similarity vs. Diversity

This paper proposes and evaluates strategies for improving retrieval diversity in CBR systems without compromising similarity or efficiency and argues that often diversity can be as important as similarity.