Abstract Details
Activity Number:
|
410
|
Type:
|
Topic Contributed
|
Date/Time:
|
Tuesday, August 11, 2015 : 2:00 PM to 3:50 PM
|
Sponsor:
|
Section on Statistical Computing
|
Abstract #315229
|
View Presentation
|
Title:
|
A Hierarchical Relational Topic Model with Latent Impact Factors for Large Document Networks
|
Author(s):
|
Linda Tan* and Tian Zheng
|
Companies:
|
National University of Singapore and Columbia University
|
Keywords:
|
relational topic model ;
document networks ;
stochastic blockmodels ;
citation prediction ;
variational methods
|
Abstract:
|
We present a hierarchical relational topic model for joint modeling of topics and citations in large document networks. The model combines the strengths of latent dirichlet allocation and mixed membership stochastic blockmodels, and associates each document with a latent impact factor. This factor provides a discipline-free measure of the impact of a document, which is measured not just by number of citations. We develop an efficient algorithm for fitting the model using variational methods. To enable the model to scale up to large networks, we develop an online variant using stochastic gradient methods. We evaluate the performance of the model using data from large citation networks and demonstrate that the model can improve citation prediction significantly.
|
Authors who are presenting talks have a * after their name.
Back to the full JSM 2015 program
|
For program information, contact the JSM Registration Department or phone (888) 231-3473.
For Professional Development information, contact the Education Department.
The views expressed here are those of the individual authors and not necessarily those of the JSM sponsors, their officers, or their staff.
2015 JSM Online Program Home
ASA Meetings Department
732 North Washington Street, Alexandria, VA 22314
(703) 684-1221 • meetings@amstat.org
Copyright © American Statistical Association.