Ontology-based topic clustering for online discussion data

Yongheng Wang; Kening Cao; Xiaoming Zhang

doi:10.1117/12.2011097

14 March 2013 Ontology-based topic clustering for online discussion data

Yongheng Wang, Kening Cao, Xiaoming Zhang

Proceedings Volume 8768, International Conference on Graphic and Image Processing (ICGIP 2012); 87683T (2013) https://doi.org/10.1117/12.2011097
Event: 2012 International Conference on Graphic and Image Processing, 2012, Singapore, Singapore

Abstract

With the rapid development of online communities, mining and extracting quality knowledge from online discussions becomes very important for the industrial and marketing sector, as well as for e-commerce applications and government. Most of the existing techniques model a discussion as a social network of users represented by a user-based graph without considering the content of the discussion. In this paper we propose a new multilayered mode to analysis online discussions. The user-based and message-based representation is combined in this model. A novel frequent concept sets based clustering method is used to cluster the original online discussion network into topic space. Domain ontology is used to improve the clustering accuracy. Parallel methods are also used to make the algorithms scalable to very large data sets. Our experimental study shows that the model and algorithms are effective when analyzing large scale online discussion data.

Citation Download Citation

Yongheng Wang, Kening Cao, and Xiaoming Zhang "Ontology-based topic clustering for online discussion data", Proc. SPIE 8768, International Conference on Graphic and Image Processing (ICGIP 2012), 87683T (14 March 2013); https://doi.org/10.1117/12.2011097

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available