Beautiful and damned. Combined effect of content quality and social ties on user engagement

TL;DR

This study investigates how the aesthetic quality of images and social network structure influence user engagement on Flickr, revealing that exposure to beautiful content can both motivate and discourage participation depending on social context.

Contribution

It introduces a deep learning model for assessing image beauty at scale and analyzes its impact on user behavior within large social networks.

Findings

Beautiful images are evenly distributed across the network.

Exposure to high-quality content can increase user content quality.

Excessive imbalance in content quality reduces user engagement.

Abstract

User participation in online communities is driven by the intertwinement of the social network structure with the crowd-generated content that flows along its links. These aspects are rarely explored jointly and at scale. By looking at how users generate and access pictures of varying beauty on Flickr, we investigate how the production of quality impacts the dynamics of online social systems. We develop a deep learning computer vision model to score images according to their aesthetic value and we validate its output through crowdsourcing. By applying it to over 15B Flickr photos, we study for the first time how image beauty is distributed over a large-scale social system. Beautiful images are evenly distributed in the network, although only a small core of people get social recognition for them. To study the impact of exposure to quality on user engagement, we set up matching experiments aimed at detecting causality from observational data. Exposure to beauty is double-edged: following people who produce high-quality content increases one's probability of uploading better photos; however, an excessive imbalance between the quality generated by a user and the user's neighbors leads to a decline in engagement. Our analysis has practical implications for improving link recommender systems.