We present TopicNets, a Web-based system for visual and interactive analysis of large sets of documents using statistical topic models. A range of visualization types and control mechanisms to support knowledge discovery are presented. These include corpus- and document-specific views, iterative topic modeling, search, and visual filtering. Drill-down functionality is provided to allow analysts to visualize individual document sections and their relations within the global topic space. Analysts can search across a dataset through a set of expansion techniques on selected document and topic nodes. Furthermore, analysts can select relevant subsets of documents and perform real-time topic modeling on these subsets to interactively visualize topics at various levels of granularity, allowing for a better understanding of the documents. A discussion of the design and implementation choices for each visual analysis technique is presented. This is followed by a discussion of three diverse use cases in which TopicNets enables fast discovery of information that is otherwise hard to find. These include a corpus of 50,000 successful NSF grant proposals, 10,000 publications from a large research center, and single documents including a grant proposal and a PhD thesis.
%0 Journal Article
%1 Gretarsson:2012:TVA:2089094.2089099
%A Gretarsson, Brynjar
%A O'Donovan, John
%A Bostandjiev, Svetlin
%A Höllerer, Tobias
%A Asuncion, Arthur
%A Newman, David
%A Smyth, Padhraic
%C New York, NY, USA
%D 2012
%I ACM
%J ACM Trans. Intell. Syst. Technol.
%K academic-reference information-visualization topic-modeling
%N 2
%P 23:1--23:26
%R 10.1145/2089094.2089099
%T TopicNets: Visual Analysis of Large Text Corpora with Topic Modeling
%U http://doi.acm.org/10.1145/2089094.2089099
%V 3
%X We present TopicNets, a Web-based system for visual and interactive analysis of large sets of documents using statistical topic models. A range of visualization types and control mechanisms to support knowledge discovery are presented. These include corpus- and document-specific views, iterative topic modeling, search, and visual filtering. Drill-down functionality is provided to allow analysts to visualize individual document sections and their relations within the global topic space. Analysts can search across a dataset through a set of expansion techniques on selected document and topic nodes. Furthermore, analysts can select relevant subsets of documents and perform real-time topic modeling on these subsets to interactively visualize topics at various levels of granularity, allowing for a better understanding of the documents. A discussion of the design and implementation choices for each visual analysis technique is presented. This is followed by a discussion of three diverse use cases in which TopicNets enables fast discovery of information that is otherwise hard to find. These include a corpus of 50,000 successful NSF grant proposals, 10,000 publications from a large research center, and single documents including a grant proposal and a PhD thesis.
@article{Gretarsson:2012:TVA:2089094.2089099,
abstract = {We present TopicNets, a Web-based system for visual and interactive analysis of large sets of documents using statistical topic models. A range of visualization types and control mechanisms to support knowledge discovery are presented. These include corpus- and document-specific views, iterative topic modeling, search, and visual filtering. Drill-down functionality is provided to allow analysts to visualize individual document sections and their relations within the global topic space. Analysts can search across a dataset through a set of expansion techniques on selected document and topic nodes. Furthermore, analysts can select relevant subsets of documents and perform real-time topic modeling on these subsets to interactively visualize topics at various levels of granularity, allowing for a better understanding of the documents. A discussion of the design and implementation choices for each visual analysis technique is presented. This is followed by a discussion of three diverse use cases in which TopicNets enables fast discovery of information that is otherwise hard to find. These include a corpus of 50,000 successful NSF grant proposals, 10,000 publications from a large research center, and single documents including a grant proposal and a PhD thesis.},
acmid = {2089099},
added-at = {2018-06-22T11:04:57.000+0200},
address = {New York, NY, USA},
articleno = {23},
author = {Gretarsson, Brynjar and O'Donovan, John and Bostandjiev, Svetlin and H\"{o}llerer, Tobias and Asuncion, Arthur and Newman, David and Smyth, Padhraic},
biburl = {https://www.bibsonomy.org/bibtex/2642814d44e5ed099eab3f7300a1c3a4c/brusilovsky},
description = {TopicNets},
doi = {10.1145/2089094.2089099},
interhash = {c7416ac0ca7435aac5fbf7c4e252b7d2},
intrahash = {642814d44e5ed099eab3f7300a1c3a4c},
issn = {2157-6904},
issue_date = {February 2012},
journal = {ACM Trans. Intell. Syst. Technol.},
keywords = {academic-reference information-visualization topic-modeling},
month = feb,
number = 2,
numpages = {26},
pages = {23:1--23:26},
publisher = {ACM},
timestamp = {2018-06-22T11:07:29.000+0200},
title = {TopicNets: Visual Analysis of Large Text Corpora with Topic Modeling},
url = {http://doi.acm.org/10.1145/2089094.2089099},
volume = 3,
year = 2012
}