2010 PETaStatisticalModelforPopularE

• (Lin et al., 2010) ⇒ Cindy Xide Lin, Bo Zhao, Qiaozhu Mei, and Jiawei Han. (2010). “PET: A Statistical Model for Popular Events Tracking in Social Communities.” In: Proceedings of the 16th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD-2010). doi:10.1145/1835804.1835922

Subject Headings:

Notes

• Categories and Subject Descriptors: H.2.8 Database Applications: Data Mining.
• General Terms: Algorithms

Cited By

• http://scholar.google.com/scholar?q=%22PET%3A+a+statistical+model+for+popular+events+tracking+in+social+communities%22+2010
• http://portal.acm.org/citation.cfm?id=1835922&preflayout=flat#citedby

Quotes

Author Keywords

PET, Popular Events Tracking, Social Communities, Topic Modeling

Abstract

User generated information in online communities has been characterized with the mixture of a text stream and a network structure both changing over time. A good example is a web-blogging community with the daily blog posts and a social network of bloggers.

An important task of analyzing an online community is to observe and track the popular events, or topics that evolve over time in the community. Existing approaches usually focus on either the burstiness of topics or the evolution of networks, but ignoring the interplay between textual topics and network structures.

In this paper, we formally define the problem of popular event tracking in online communities (PET), focusing on the interplay between texts and networks. We propose a novel statistical method that models the the popularity of events over time, taking into consideration the burstiness of user interest, information diffusion on the network structure, and the evolution of textual topics. Specifically, a Gibbs Random Field is defined to model the influence of historic status and the dependency relationships in the graph; thereafter a topic model generates the words in text content of the event, regularized by the Gibbs Random Field. We prove that two classic models in information diffusion and text burstiness are special cases of our model under certain situations. Empirical experiments with two different communities and datasets (i.e., Twitter and DBLP) show that our approach is effective and outperforms existing approaches.

References

,

	Author	volume	Date Value	title	type	journal	titleUrl	doi	note	year
2010 PETaStatisticalModelforPopularE	Qiaozhu Mei Cindy Xide Lin Bo Zhao Jiawei Han			PET: A Statistical Model for Popular Events Tracking in Social Communities		KDD-2010 Proceedings	http://www.cs.uiuc.edu/~hanj/pdf/kdd10 xlin.pdf	10.1145/1835804.1835922		2010