Linking endogenous and exogenous popularity processes in social media
Authors:
Preprint
Abstract
Explaining and predicting popularity of an online item is an important problem in both the science of collective behavior, and the practice of managing information dissemination and consumption. Many recent work advance our understanding of popularity, but one notable gap remains: to precisely quantify the relationship between external promotions and subsequent popularity dynamics. This work supplies the missing link between the exogenous input and endogenous response within a social network. This is done via a novel mathematical model, called the Hawkes intensity process, that explains the complex popularity history of each video according to its content, network, and sensitivity to promotion. This model supplies a prototypical description of videos, called an endo-exo map, which allows us to explain the popularity as the joint effects of two intrinsic measures and the amount of discussions from the outside world. This model also allows us to forecast the effects of future promotions more accurately than approaches based on popularity history alone, and to identify videos that has a high potential to become viral, or those for which promotions will have hardly any effect.Keywords
All Related Versions
This publication has 14 references indexed in Scilit:
- Dynamics of news events and social media reaction2014
- Finding progression stages in time-evolving event sequences2014
- How to Schedule a Cascade in an Arbitrary GraphSIAM Journal on Computing, 2014
- Limited communication capacity unveils strategies for human interactionScientific Reports, 2013
- Predicting the popularity of online contentCommunications of the ACM, 2010
- Power-Law Distributions in Empirical DataSIAM Review, 2009
- Robust dynamic classes revealed by measuring the response function of a social systemProceedings of the National Academy of Sciences, 2008
- Subcritical and supercritical regimes in epidemic models of earthquake aftershocksJournal of Geophysical Research, 2002
- Seismicity Analysis through Point-process Modeling: A ReviewPure and Applied Geophysics, 1999
- On the limited memory BFGS method for large scale optimizationMathematical Programming, 1989