A dashboard for controlling polarization in personalization

Issue title: IJCAI-ECAI-18 Demonstration Track

Guest editors: Paul Weng

Article type: Research Article

Authors: Celis, L. Elisa^{a; *} | Kapoor, Sayash^b | Salehi, Farnood^c | Keswani, Vijay^d | Vishnoi, Nisheeth K.^e

Affiliations: [a] Statistics & Data Science, Yale University, USA. E-mail: [email protected] | [b] Department of CSE, IIT Kanpur, India. E-mail: [email protected] | [c] Department of IC, EPFL, Switzerland. E-mail: [email protected] | [d] Department of IC, EPFL, Switzerland. E-mail: [email protected] | [e] Computer Science, Yale University, USA. E-mail: [email protected]

Correspondence: [*] Corresponding author. E-mail: [email protected].

Abstract: Personalization is pervasive in the online space as it leads to higher efficiency for the user and higher revenue for the platform by individualizing the most relevant content for each user. However, recent studies suggest that such personalization can learn and propagate systemic biases and polarize opinions; this has led to calls for regulatory mechanisms and algorithms that are constrained to combat bias and the resulting echo-chamber effect. We present our balanced news feed via a demo that displays a dashboard through which users can view the political leaning of their news consumption and set their polarization constraints. The balanced feed, as generated by the user-defined constraints, is then showcased side-by-side with the unconstrained (polarized) feed for comparison.

Keywords: Polarization, constrained optimization, personalization, fairness, demo

DOI: 10.3233/AIC-180606

Journal: AI Communications, vol. 32, no. 1, pp. 77-89, 2019