Title :
TopicView: Visually Comparing Topic Models of Text Collections
Author :
Crossno, Patricia J. ; Wilson, Andrew T. ; Shead, Timothy M. ; Dunlavy, Daniel M.
Author_Institution :
Scalable Anal. & Visualization, Sandia Nat. Labs., Albuquerque, NM, USA
Abstract :
We present Topic View, an application for visually comparing and exploring multiple models of text corpora. Topic View uses multiple linked views to visually analyze both the conceptual content and the document relationships in models generated using different algorithms. To illustrate Topic View, we apply it to models created using two standard approaches: Latent Semantic Analysis (LSA) and Latent Dirichlet Allocation (LDA). Conceptual content is compared through the combination of (i) a bipartite graph matching LSA concepts with LDA topics based on the cosine similarities of model factors and (ii) a table containing the terms for each LSA concept and LDA topic listed in decreasing order of importance. Document relationships are examined through the combination of (i) side-by-side document similarity graphs, (ii) a table listing the weights for each document´s contribution to each concept/topic, and (iii) a full text reader for documents selected in either of the graphs or the table. We demonstrate the utility of Topic View´s visual approach to model assessment by comparing LSA and LDA models of two example corpora.
Keywords :
content management; data visualisation; graph theory; text analysis; LDA topics; TopicView; bipartite graph matching LSA concepts; conceptual content analysis; cosine similarities; document relationships; latent Dirichlet allocation; latent semantic analysis; model assessment; model factors; multiple linked views; side-by-side document similarity graphs; text collection; text corpora; text reader; topic model; visual model analysis; Analytical models; Bipartite graph; Computational modeling; Data models; Layout; Vectors; Visualization; latent dirichlet allocation; latent semantic analysis; text analysis; visual model analysis;
Conference_Titel :
Tools with Artificial Intelligence (ICTAI), 2011 23rd IEEE International Conference on
Conference_Location :
Boca Raton, FL
Print_ISBN :
978-1-4577-2068-0
Electronic_ISBN :
1082-3409
DOI :
10.1109/ICTAI.2011.162