Emergence of scale-free leadership structure in social recommender systems

TL;DR

This paper analyzes social networks from major platforms, revealing a scale-free leadership structure, and introduces an adaptive model driven by social recommending that explains the emergence of influential leaders and improves user experience.

Contribution

It provides empirical evidence of scale-free leadership in social networks and proposes a novel adaptive social recommending model that explains leadership emergence and enhances user engagement.

Findings

Social networks exhibit a scale-free leadership structure.

The proposed model reproduces leadership emergence through a 'good get richer' mechanism.

Social recommending can improve user experience by adapting to individual tastes.

Abstract

The study of the organization of social networks is important for understanding of opinion formation, rumor spreading, and the emergence of trends and fashion. This paper reports empirical analysis of networks extracted from four leading sites with social functionality (Delicious, Flickr, Twitter and YouTube) and shows that they all display a scale-free leadership structure. To reproduce this feature, we propose an adaptive network model driven by social recommending. Artificial agent-based simulations of this model highlight a "good get richer" mechanism where users with broad interests and good judgments are likely to become popular leaders for the others. Simulations also indicate that the studied social recommendation mechanism can gradually improve the user experience by adapting to tastes of its users. Finally we outline implications for real online resource-sharing systems.