Beautiful and Damned. Combined Effect of Content Quality and Social Ties on 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.

Understanding the effects of personality traits on solver engagement in crowdsourcing communities: a moderated mediation investigation

“…Solver engagement describes the subjective psychological state that occurs by virtue of interaction and co-creative user experiences in online crowdsourcing environments (Brodie et al , 2013; Huang et al , 2019; Ihl et al , 2020). In essence, engagement denotes the extent to which an individual is active in different kinds of activities (Aiello et al , 2017; Cf et al , 2003; Troll et al , 2019). Solvers engaged in online crowdsourcing communities help nurture strong psychological connections that promote solvers' contribution behavior and a long-lasting relationship with the community (Rich et al , 2010; Yang et al , 2019a).…”

The Strength of Structural Diversity in Online Social Networks

“…Propensity score matching (PSM) is a widely used method for matching experiments in the literature [25,[56][57][58][59][60][61]. The key intuition of PSM is to match the treatment group with a control group whose members do not receive the treatment but are statistically indistinguishable or at least only marginally different (within a reasonable limit) from the treatment group on all observable covariates.…”

The Strength of Structural Diversity in Online Social Networks

“…Propensity score matching (PSM) is a widely used method for matching experiments in the literature 27,[34][35][36][37] . The key intuition of PSM is to match the treatment group with a control group whose members don't receive the treatment but are statistically indistinguishable or at least only marginally different (within a reasonable limit) from the treatment group on all observable covariates.…”