Learning to Suggest Breaks: Sustainable Optimization of Long-Term User Engagement

TL;DR

This paper introduces a novel framework for learning optimal break policies in recommendation systems to enhance long-term user engagement and digital well-being, using a dynamical systems approach and optimal control theory.

Contribution

It models recommendation dynamics as a Lotka-Volterra system and develops an efficient learning algorithm with theoretical guarantees for optimal break scheduling.

Findings

Effective learning algorithm for break policies

Theoretical guarantees for policy optimality

Empirical validation on semi-synthetic data

Abstract

Optimizing user engagement is a key goal for modern recommendation systems, but blindly pushing users towards increased consumption risks burn-out, churn, or even addictive habits. To promote digital well-being, most platforms now offer a service that periodically prompts users to take breaks. These, however, must be set up manually, and so may be suboptimal for both users and the system. In this paper, we study the role of breaks in recommendation, and propose a framework for learning optimal breaking policies that promote and sustain long-term engagement. Based on the notion that recommendation dynamics are susceptible to both positive and negative feedback, we cast recommendation as a Lotka-Volterra dynamical system, where breaking reduces to a problem of optimal control. We then give an efficient learning algorithm, provide theoretical guarantees, and empirically demonstrate the utility of our approach on semi-synthetic data.