Faithfully Explaining Rankings in a News Recommender System

TL;DR

This paper introduces LISTEN, a novel method for explaining the rankings in news recommender systems, and demonstrates its faithfulness and safety in real-world user interactions.

Contribution

The paper proposes LISTEN, the first method to explain ranking outcomes, and develops Q-LISTEN, a neural network that efficiently learns these explanations for practical deployment.

Findings

LISTEN provides faithful explanations of ranking algorithms.

Q-LISTEN successfully learns explanations generated by LISTEN.

User behavior remains unaffected when exposed to LISTEN-generated explanations.

Abstract

There is an increasing demand for algorithms to explain their outcomes. So far, there is no method that explains the rankings produced by a ranking algorithm. To address this gap we propose LISTEN, a LISTwise ExplaiNer, to explain rankings produced by a ranking algorithm. To efficiently use LISTEN in production, we train a neural network to learn the underlying explanation space created by LISTEN; we call this model Q-LISTEN. We show that LISTEN produces faithful explanations and that Q-LISTEN is able to learn these explanations. Moreover, we show that LISTEN is safe to use in a real world environment: users of a news recommendation system do not behave significantly differently when they are exposed to explanations generated by LISTEN instead of manually generated explanations.