Understanding or Manipulation: Rethinking Online Performance Gains of Modern Recommender Systems

TL;DR

This paper introduces a framework to measure how much recommendation algorithms manipulate user preferences, revealing that higher click rates may not indicate better understanding but increased manipulation, influenced by training data and model complexity.

Contribution

The paper proposes a novel benchmarking framework with metrics to quantify user preference manipulation in recommender systems, highlighting the impact of training data and model power.

Findings

High click-through does not imply better preference understanding.

Training data significantly affects manipulation levels.

Proposed metrics effectively measure manipulation degree.

Abstract

Recommender systems are expected to be assistants that help human users find relevant information automatically without explicit queries. As recommender systems evolve, increasingly sophisticated learning techniques are applied and have achieved better performance in terms of user engagement metrics such as clicks and browsing time. The increase in the measured performance, however, can have two possible attributions: a better understanding of user preferences, and a more proactive ability to utilize human bounded rationality to seduce user over-consumption. A natural following question is whether current recommendation algorithms are manipulating user preferences. If so, can we measure the manipulation level? In this paper, we present a general framework for benchmarking the degree of manipulations of recommendation algorithms, in both slate recommendation and sequential recommendation scenarios. The framework consists of four stages, initial preference calculation, training data collection, algorithm training and interaction, and metrics calculation that involves two proposed metrics. We benchmark some representative recommendation algorithms in both synthetic and real-world datasets under the proposed framework. We have observed that a high online click-through rate does not necessarily mean a better understanding of user initial preference, but ends in prompting users to choose more documents they initially did not favor. Moreover, we find that the training data have notable impacts on the manipulation degrees, and algorithms with more powerful modeling abilities are more sensitive to such impacts. The experiments also verified the usefulness of the proposed metrics for measuring the degree of manipulations. We advocate that future recommendation algorithm studies should be treated as an optimization problem with constrained user preference manipulations.