Exposure diversity as a design principle for recommender systems

Abstract

Exposure diversity as a design principle for recommender systemsHelberger, N.; Karpinnen, K.; D'Acunto, L. General rightsIt is not permitted to download or to forward/distribute the text or part of it without the consent of the author(s) and/or copyright holder(s), other than for strictly personal, individual use, unless the work is under an open content license (like Creative Commons). Disclaimer/Complaints regulationsIf you believe that digital publication of certain material infringes any of your rights or (privacy) interests, please let the Library know, stating your reasons. In case of a legitimate complaint, the Library will make the material inaccessible and/or remove it from the website. Please Ask the Library: http://uba.uva.nl/en/contact, or a letter to: Library of the University of Amsterdam, Secretariat, Singel 425, 1012 WP Amsterdam, The Netherlands. You will be contacted as soon as possible. ABSTRACTPersonalized recommendations in search engines, social media and also in more traditional media increasingly raise concerns over potentially negative consequences for diversity and the quality of public discourse. The algorithmic filtering and adaption of online content to personal preferences and interests is often associated with a decrease in the diversity of information to which users are exposed. Notwithstanding the question of whether these claims are correct or not, this article discusses whether and how recommendations can also be designed to stimulate more diverse exposure to information and to break potential 'filter bubbles' rather than create them. Combining insights from democratic theory, computer science and law, the article makes suggestions for design principles and explores the potential and possible limits of 'diversity sensitive design'. IntroductionRecommendation systems increasingly influence our information choices: the information that is ultimately being presented to us has been filtered through the lens of our personal preferences, our previous choices and the preferences of our friends. There are also commercial and strategic decisions behind the algorithms that determine which information we will see, which information is prioritized and which information is excluded (Bozdag, 2013;Foster, 2012;Schulz, Dreyer, & Hagemeier, 2012;Webster, 2010). Search engines and social networks, in particular, increasingly rely on recommender systems, which are a class of information filtering systems that study patterns of user behaviour to determine what someone will prefer from among a collection of 'information'. By doing so, recommender systems essentially personalize the list of content that is offered to a user. With the emerging trends of higher interactivity and user orientation, the use of recommender systems is not limited to search engines and social networks, as media organizations are also increasingly incorporating recommenders into their own services.The impact of personalized recommendations on the realization of media and information diversity is currently a central questi...

Democratizing algorithmic news recommenders: how to materialize voice in a technologically saturated media ecosystem

“…One can think of diversity in terms of ideological background, professional origin, writing and presentation style, article length, and so on. A growing literature on diversity in relation to the digital news environment can support conceptualizing diversity further and developing the relevant algorithms accordingly [22].…”

“…But if the context is a news aggregator, then it is also about missing certain ideological perspectives (cf. [21][22][23][24]). 2 ANR may, for example, help people deal with today's information-saturated world by pre-selecting what is relevant for each individual (cf.…”

Holarchic structures for decentralized deep learning: a performance analysis

“…The Internet of Things empowers a high level of interconnectivity between smart phones, sensors and wearable devices. These technological developments provide unprecedented opportunities to rethink about the future of machine learning and artificial intelligence: Centralized computational intelligence can be often used for privacy-intrusive and discriminatory services that create 'filter bubbles' and undermine citizens' autonomy by nudging [12,31,17]. In contrast, this paper envisions a more socially responsible design for digital society based on decentralized learning and collective intelligence formed by bottomup planetary-scale networks run by citizens [38,18].…”

Challenged by news personalisation: five perspectives on the right to receive information

“…134 Personalisation could provide similar nudges. At the same time, scholars have predicted that under the right conditions, exposure diversity rather than exposure to similar content could benefit social cohesion, 135 so stimulating diverse or shared content should be carefully implemented.…”