Performative Recommendation: Diversifying Content via Strategic Incentives

TL;DR

This paper introduces a novel recommendation approach that incentivizes content creators to produce diverse content by leveraging the performative nature of recommendations and a new regularization method, promoting sustained diversity.

Contribution

It proposes a new regularization technique that anticipates strategic content creation, encouraging inherent diversity rather than just re-ranking existing items.

Findings

The approach effectively incentivizes diverse content creation in synthetic settings.

Analytic results show conditions under which diversity incentives work.

Empirical experiments validate the method's utility on synthetic data.

Abstract

The primary goal in recommendation is to suggest relevant content to users, but optimizing for accuracy often results in recommendations that lack diversity. To remedy this, conventional approaches such as re-ranking improve diversity by presenting more diverse items. Here we argue that to promote inherent and prolonged diversity, the system must encourage its creation. Towards this, we harness the performative nature of recommendation, and show how learning can incentivize strategic content creators to create diverse content. Our approach relies on a novel form of regularization that anticipates strategic changes to content, and penalizes for content homogeneity. We provide analytic and empirical results that demonstrate when and how diversity can be incentivized, and experimentally demonstrate the utility of our approach on synthetic and semi-synthetic data.