A learning-based model for predicting information diffusion in social networks: Case of Twitter - Université de Lorraine
Conference Papers Year : 2016

A learning-based model for predicting information diffusion in social networks: Case of Twitter

Abstract

Diffusion action is a key behavior of users in online social networks. This action may further propagate to other connections of the users and affect their actions. Recent research has focused on studying the diffusion action of users, particularly, predicting information diffusion in future. However, most of current diffusion models mainly focus on giving general model of diffusion. In this paper, we propose a model of information diffusion prediction which analyzes all factors affecting users' diffusion decision such as user features, link features and crowd-features. In addition, we take into account the presence of multi-topics in the content item. We validate our model by conducting experiments on a snapshot of Twitter containing tweets and retweets involving French media, which demonstrates the interest of our model.
No file

Dates and versions

hal-01785905 , version 1 (04-05-2018)

Identifiers

Cite

Bao-Thien Hoang, Kamel Chelghoum, Imed Kacem. A learning-based model for predicting information diffusion in social networks: Case of Twitter. 2016 International Conference on Control, Decision and Information Technologies (CoDIT), Apr 2016, Saint Julian's, Malta. ⟨10.1109/CoDIT.2016.7593657⟩. ⟨hal-01785905⟩
41 View
0 Download

Altmetric

Share

More