Eventdetails

Supporting User Control for Diverse Item Recommendations

Type

• Veranstaltungsreihe

Topic

• Information Communication & Computing (Field of Expertise)

Recommender systems find relevant content for us online, including the personalized news that we increasingly receive on Twitter and Facebook. As a consequence of personalization we increasingly see content that agrees with our views. However, understanding and finding solutions to complex issues often requires us to view those issues from a variety of perspectives. Echo chambers can become problematic when the similarity of opinion leads to more extreme or polarising views. We only hear those who agree with us, and more extreme positions therefore start to seem more reasonable to us.

This talk considers a solution using interaction paradigms, and methods for generating explanation interfaces. Such explanations can be used to improve trust and transparency, but they can also be used to improve the discovery of novel content and help users identify their own blindspots. This talk introduces a vision of information presentation strategies which help users accept surprising content, and present opposing content in a way that is acceptable to them. In doing so, diversity-aware design solutions can address both user and algorithmic biases, and have a greater potential to decrease polarization of views.

About Nava Tintarev

Nava Tintarev is an Assistant Professor and Technology Fellow at Delft University of Technology. She completed her PhD at the University of Aberdeen in 2010, and was previously an Assistant Professor at Bournemouth University (UK). Her research looks at how to improve the transparency and decision support for recommender systems. She in on the management team for Delft Design for Values, and is contributing to bringing together, integrating, and expanding existing practices and expertise for responsible data science. She acts as a senior member of the program committee for the ACM Conference on Intelligent User Interfaces, the ACM Recommender Systems Conference, and the Conference on User Modeling Adaptation and Personalization. She will be serving as a Program co-Chair for the Intelligent User Interfaces conference in 2020.

Host

TU Graz | Faculty of Computer Science and Biomedical Engineering