Virality Prediction and Community Structure in Social Networks

By L. Weng, Filippo Menczer, Yong-Yeol Ahn. 2013

666 citations recorded by the source corpus.

How does network structure affect diffusion? Recent studies suggest that the answer depends on the type of contagion. Complex contagions, unlike infectious diseases (simple contagions), are affected by social reinforcement and homophily. Hence, the spread within highly clustered communities is enhanced, while diffusion across communities is hampered. A common hypothesis is that memes and behaviors are complex contagions. We show that, while most memes indeed spread like complex contagions, a few viral memes spread across many communities, like diseases. We demonstrate that the future popularity of a meme can be predicted by quantifying its early spreading pattern in terms of community concentration. The more communities a meme permeates, the more viral it is. We present a practical method to translate data about community structure into predictive knowledge about what information will spread widely. This connection contributes to our understanding in computational social science, social media analytics and marketing applications.

Subfields: Sociology and Political Science, Statistical and Nonlinear Physics

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Sociology and Political Science

In Statistical and Nonlinear Physics

Citations in the corpus

How algorithmic popularity bias hinders or promotes quality (2017, background): “@gmail.com 1 arXiv:1707.00574v2 [cs.CY] 14 Jul 2017 unpredictability. Success of individual actors (e.g., artists) or products (e.g., songs, movies, memes) is in fact hard to predict in these systems [34, 35, 25], mainly due to the presence of strong social reinforcement, information cascades, and t”
Can cascades be predicted? (2014, background): “Previous work considered the network structure of the underlying graph in inferring the virality of content [32], with highly viral items spreading across communities.”
DeepHawkes: Bridging the Gap between Prediction and Understanding of Information Cascades (2017, background): “These features mainly include temporal features [2, 3], structural features [16, 18, 19], content features [15, 20–22] and features defined on early adopters [13, 23, 24].”
Dynamics of information diffusion and its applications on complex networks (2016, background): “Another application of threshold model is to study the influence of community structure on information diffusion [12,191].”
Testing Propositions Derived from Twitter Studies: Generalization and Replication in Computational Social Science (2015, background): “Further studies found that the relationship could vary across topics [45], across number of friends due to the information overload of highly connected users [46, 47], and across community structures [48].”
Insights on Transfer Optimization: Because Experience is the Best Teacher (2018, background): “In particular, the interconnected web of problems will make it possible for knowledge memes generated at any node to propagate throughout the network (mimicking the viral effect [95]), such that other problem-solving exercises can immediately benefit from related experiences elsewhere.”
Digital Footprints: Opportunities and Challenges for Online Social Research (2014, result): “More recently, Weng et al. (2013) used Twitter hashtags to confirm a key implication of the theory of complex contagions— that the spread of complex contagions depends on network structure, a result that is consistent with the experimental findings reported by Centola (noted above).”