DocumentCode :
3078357
Title :
A Tool for Visualizing Topic Evolution in Large Text Collections
Author :
Feipeng Sun ; Yanyan Li ; Zhiqiang Zhang
Author_Institution :
R&D Center for Knowledge Eng., Beijing Normal Univ., Beijing, China
fYear :
2013
fDate :
15-18 July 2013
Firstpage :
53
Lastpage :
54
Abstract :
Topic evolution in text data has become a flourishing frontier in the text mining community. Yet with the increasing number of texts, it is important and challenging to understand how topics evolve. In this paper, we introduce a tool to analyze various evolution patterns that emerge from multiple texts based on combination of topic modeling and visualization techniques. By mining topic hierarchical relationship and evolutionary trend, the tool provides three visualization views along with interactive functionality that enables users to understand the topic evolution in a flexible and easily way. Experiment on real dataset has shown that the developed tool is effective to visualizing meaningful topic evolution in large text collections.
Keywords :
data mining; data visualisation; text analysis; evolution patterns; interactive functionality; large text collection; text data; text mining community; topic evolution visualisation; topic modeling; topic visualisation; visualization techniques; Conferences; Data models; Data visualization; Educational institutions; Market research; Resource management; Visualization; Hierarchical Latent Dirichlet Allocation; Topic evolution; interaction design; visualization;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Advanced Learning Technologies (ICALT), 2013 IEEE 13th International Conference on
Conference_Location :
Beijing
Type :
conf
DOI :
10.1109/ICALT.2013.21
Filename :
6601864
Link To Document :
بازگشت