This paper introduces a temporal framework for detecting and clustering emergent and viral topics on social networks. Endogenous and exogenous influence on developing viral content is explored using a clustering method based on the a user's behavior on social network and a dataset from Twitter API. Results are discussed by introducing metrics such as popularity, burstiness, and relevance score. The results show clear distinction in characteristics of developed content by the two classes of users.
@article{arxiv.1811.07655,
title = {An Influence-based Clustering Model on Twitter},
author = {Abbas Ehsanfar and Mo Mansouri},
journal= {arXiv preprint arXiv:1811.07655},
year = {2018}
}
Comments
INFORMS 13th Data Mining and Decision Analytics Workshop