|
Title:
|
CONTENT AND COMMUNICATION BASED SUBCOMMUNITY DETECTION USING PROBABILISTIC TOPIC MODELS |
|
Author(s):
|
Alexandru Berlea , Markus Döhring , Nicolai Reuschling |
|
ISBN:
|
978-972-8924-87-4 |
|
Editors:
|
António Palma dos Reis |
|
Year:
|
2009 |
|
Edition:
|
Single |
|
Keywords:
|
Community Mining, Topic Detection, Probabilistic Models, Social Network Analysis |
|
Type:
|
Full Paper |
|
First Page:
|
19 |
|
Last Page:
|
26 |
|
Language:
|
English |
|
Cover:
|
|
|
Full Contents:
|
click to dowload 
|
|
Paper Abstract:
|
Sub-community detection is a fundamental task in social network analysis and becomes increasingly interesting in
business applications related to supporting collaboration platforms on the Internet and mining the content generated on
them. We present a set of methods for sub-community detection leveraging on probabilistic topic models. The methods
are based on similarities among community members arising from their communication links, their topics of interest, or
on both aspects. We thereby identify suitable scenarios for the application of the proposed approaches. Preliminary
experimental results indicate our hybrid approach as a promising candidate for the analysis of large forum communities. |
|
|
|
|
|
|
