Predictability of extreme events in social media

Abstract

It is part of our daily social-media experience that seemingly ordinary items (videos, news, publications, etc.) unexpectedly gain an enormous amount of attention. Here we investigate how unexpected these events are. We propose a method that, given some information on the items, quantifies the predictability of events, i.e., the potential of identifying in advance the most successful items defined as the upper bound for the quality of any prediction based on the same information. Applying this method to different data, ranging from views in YouTube videos to posts in Usenet discussion groups, we invariantly find that the predictability increases for the most extreme events. This indicates that, despite the inherently stochastic collective dynamics of users, efficient prediction is possible for the most extreme events.

arXiv comment13 pages, 3 figures

References in corpus (16)

• Statistical physics of social dynamics
• Quantifying Long-Term Scientific Impact
• Robust dynamic classes revealed by measuring the response function of a social system
• Novelty and Collective Attention
• The Matthew effect in empirical data
• Predictability of catastrophic events: material rupture, earthquakes, turbulence, financial crashes and human birth
• The Spontaneous Emergence of Social Influence in Online Systems
• Characterizing and modeling the dynamics of online popularity
• Endogenous Versus Exogenous Shocks in Complex Networks: an Empirical Test Using Book Sale Ranking
• On the Predictability of Future Impact in Science
• Reliability, Sufficiency, and the Decomposition of Proper Scores
• The Pulse of News in Social Media: Forecasting Popularity
• On sampling and modeling complex systems
• Niche as a determinant of word fate in online groups
• A maximum entropy framework for non-exponential distributions
• Precursors of extreme increments

Cited by in corpus (13)

• The effects of network structure, competition and memory time on social spreading phenomena
• A maximum entropy framework for non-exponential distributions
• Investigating Political Participation and Social Information Using Big Data and a Natural Experiment
• Twitter-based analysis of the dynamics of collective attention to political parties
• Local variation of hashtag spike trains and popularity in Twitter
• Impact of lexical and sentiment factors on the popularity of scientific papers
• Predictability of Critical Transitions
• Predictability of threshold exceedances in dynamical systems
• Quantifying Uncertainty in a Predictive Model for Popularity Dynamics
• Stochastic dynamics and the predictability of big hits in online videos
• Local Variation of Collective Attention in Hashtag Spike Trains
• The role of emotional variables in the classification and prediction of collective social dynamics
• Predicting Engagement with the Internet Research Agency's Facebook and Instagram Campaigns around the 2016 U.S. Presidential Election