Tweet Ranking based on Heterogeneous Networks

Hongzhao Huang, Arkaitz Zubiaga, Heng Ji, Hongbo Deng, Dong Wang, Hieu Khac Le, Tarek Abdelzaher, Jiawei Han, Alice Leung, John Hancock, Clare Voss

COLING. 2012.

Ranking tweets is a fundamental task to make it easier to distill the vast amounts of information shared by users. In this paper, we explore the novel idea of ranking tweets on a topic using heterogeneous networks. We construct heterogeneous networks by harnessing cross-genre linkages between tweets and semantically related web documents from formal genres, besides inferring implicit linkages between tweets and users. To rank effectively by capturing semantic meanings and importance of different linkages, we introduce Tri-HITS, a model to iteratively propagate ranking scores across heterogeneous networks. We show that integrating a formal genre and inferring implicit social networks produces a high quality ranking that tweets on their own cannot.

Download PDF file