Skip to Main content Skip to Navigation
Conference papers

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.
Document type :
Conference papers
Complete list of metadata

https://hal.univ-lorraine.fr/hal-01785905
Contributor : Lcoms Ul <>
Submitted on : Friday, May 4, 2018 - 4:46:06 PM
Last modification on : Saturday, May 5, 2018 - 1:19:21 AM

Identifiers

Collections

Citation

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⟩

Share

Metrics

Record views

88