Beyond clicks

TLDR

Content recommendation systems from major internet companies aim to personalize user experiences, which is believed to boost long‑term engagement, yet directly optimizing for user satisfaction remains challenging. The paper investigates using item‑level dwell time as a proxy for content relevance to users. The authors compute accurate dwell time from client‑side and server‑side logs, normalize it across devices, and integrate it into learning‑to‑rank and collaborative filtering models. These experiments demonstrate that incorporating dwell time yields competitive performance in both offline and online evaluations.

Abstract

Many internet companies, such as Yahoo, Facebook, Google and Twitter, rely on content recommendation systems to deliver the most relevant content items to individual users through personalization. Delivering such personalized user experiences is believed to increase the long term engagement of users. While there has been a lot of progress in designing effective personalized recommender systems, by exploiting user interests and historical interaction data through implicit (item click) or explicit (item rating) feedback, directly optimizing for users' satisfaction with the system remains challenging. In this paper, we explore the idea of using item-level dwell time as a proxy to quantify how likely a content item is relevant to a particular user. We describe a novel method to compute accurate dwell time based on client-side and server-side logging and demonstrate how to normalize dwell time across different devices and contexts. In addition, we describe our experiments in incorporating dwell time into state-of-the-art learning to rank techniques and collaborative filtering models that obtain competitive performances in both offline and online settings.