Srijith, P K and Lukasik, M and Bontcheva, K and Cohn, T
(2017)
Longitudinal Modeling of Social Media with Hawkes Process based on Users and Networks.
In: IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM), 31 July - 03 August, 2017, Sydney, Australia.
Abstract
Online social networks provide a platform for
sharing information at an unprecedented scale. Users generate
information which propagates across the network resulting in
information cascades. In this paper, we study the evolution of
information cascades in Twitter using a point process model
of user activity. We develop several Hawkes process models
considering various properties including conversational structure,
users’ connections and general features of users including the
textual information, and show how they are helpful in modeling
the social network activity. We consider low-rank embeddings
of users and user features, and learn the features helpful in
identifying the influence and susceptibility of users. Evaluation
on Twitter data sets associated with civil unrest shows that
incorporating richer properties improves the performance in
predicting future activity of users and memes.
Actions (login required)
 |
View Item |
Altmetric
Altmetric