TY - JOUR
T1 - Identifying exogenous and endogenous activity in social media
AU - Fujita, Kazuki
AU - Medvedev, Alexey
AU - Koyama, Shinsuke
AU - Lambiotte, Renaud
AU - Shinomoto, Shigeru
N1 - Funding Information:
The authors would like to offer a special thanks to Alexandre Bovet for sharing the Twitter data. This study was supported in part by Grants-in-Aid for Scientific Research to S.S. from JSPS KAKENHI Grants No. 26280007 and No. 17H06028 and JST CREST Grant Number JPMJCR1304. A.M., R.L., and S.S. were supported by the Bilateral Joint Research Project between JSPS, Japan and FRS-FNRS, Belgium. A.M. was supported by ARC (Federation Wallonia-Brussels) and by the Russian Foundation of Basic Research (16-01-00499).
Funding Information:
This study was supported in part by Grants-in-Aid for Scientific Research to S.S. from JSPS KAKENHI Grants No. 26280007 and No. 17H06028 and JST CREST Grant Number JPMJCR1304. A.M., R.L., and S.S. were supported by the Bilateral Joint Research Project between JSPS, Japan and FRS-FNRS, Belgium. A.M. was supported by ARC (Federation Wallonia-Brussels) and by the Russian Foundation of Basic Research (16-01-00499).
Publisher Copyright:
© 2018 American Physical Society.
Copyright:
Copyright 2018 Elsevier B.V., All rights reserved.
PY - 2018/11/13
Y1 - 2018/11/13
N2 - The occurrence of new events in a system is typically driven by external causes and by previous events taking place inside the system. This is a general statement, applying to a range of situations including, more recently, to the activity of users in online social networks (OSNs). Here we develop a method for extracting from a series of posting times the relative contributions that are exogenous, e.g., news media, and endogenous, e.g., information cascade. The method is based on the fitting of a generalized linear model (GLM) equipped with a self-excitation mechanism. We test the method with synthetic data generated by a nonlinear Hawkes process, and apply it to a real time series of tweets with a given hashtag. In the empirical dataset, the estimated contributions of exogenous and endogenous volumes are close to the amounts of original tweets and retweets respectively. We conclude by discussing the possible applications of the method, for instance in online marketing.
AB - The occurrence of new events in a system is typically driven by external causes and by previous events taking place inside the system. This is a general statement, applying to a range of situations including, more recently, to the activity of users in online social networks (OSNs). Here we develop a method for extracting from a series of posting times the relative contributions that are exogenous, e.g., news media, and endogenous, e.g., information cascade. The method is based on the fitting of a generalized linear model (GLM) equipped with a self-excitation mechanism. We test the method with synthetic data generated by a nonlinear Hawkes process, and apply it to a real time series of tweets with a given hashtag. In the empirical dataset, the estimated contributions of exogenous and endogenous volumes are close to the amounts of original tweets and retweets respectively. We conclude by discussing the possible applications of the method, for instance in online marketing.
KW - physics.soc-ph
KW - cs.SI
UR - http://www.scopus.com/inward/record.url?scp=85056639762&partnerID=8YFLogxK
U2 - 10.1103/PhysRevE.98.052304
DO - 10.1103/PhysRevE.98.052304
M3 - Article
VL - 98
JO - ArXiv pre-print
JF - ArXiv pre-print
IS - 5
M1 - 052304
ER -