Collective topic modeling for heterogeneous networks

In this paper, we propose a joint probabilistic topic model for simultaneously modeling the contents of multi-typed objects of a heterogeneous information network. The intuition behind our model is that different objects of the heterogeneous network share a common set of latent topics so as to adjust the multinomial distributions over topics for different objects collectively. Experimental results demonstrate the effectiveness of our approach for the tasks of topic modeling and object clustering. Categories and Subject Descriptors: H.3.3 [Information Storage and Retrieval]: Information Search and Retrieval—text mining, clustering General Terms: Algorithms, Experimentation

• Type: Journal
• Year: 2011
• Where: SIGIR
• Authors: Hongbo Deng, Bo Zhao, Jiawei Han
• Keywords: Heterogeneous Network, Information Storage And Retrieval, Information Technology, SIGIR 2011, Subject Descriptors