Information Cocoons in Online Navigation

TL;DR

This paper defines the concept of information cocoons in online navigation, analyzes their formation in real recommendation networks, and proposes a new recommendation strategy to mitigate ICs and enhance system navigability.

Contribution

It introduces a formal definition of information cocoons, analyzes their impact in real-world networks, and proposes a novel recommendation method to reduce IC effects and improve navigation.

Findings

Similarity-based recommendations create strong ICs that limit navigation.

Proposed strategy reduces IC effects and enhances retrieval accuracy.

Online experiments confirm the effectiveness of the new recommendation approach.

Abstract

Social media and online navigation bring us enjoyable experience in accessing information, and simultaneously create information cocoons (ICs) in which we are unconsciously trapped with limited and biased information. We provide a formal definition of IC in the scenario of online navigation. Subsequently, by analyzing real recommendation networks extracted from Science, PNAS and Amazon websites, and testing mainstream algorithms in disparate recommender systems, we demonstrate that similarity-based recommendation techniques result in ICs, which suppress the system navigability by hundreds of times. We further propose a flexible recommendation strategy that solves the IC-induced problem and improves retrieval accuracy in navigation, demonstrated by simulations on real data and online experiments on the largest video website in China.