DMCA
Termite: Visualization techniques for assessing textual topic models (2012)
| Venue: | In Proceedings of the International Working Conference on Advanced Visual Interfaces |
| Citations: | 26 - 3 self |
BibTeX
@INPROCEEDINGS{Chuang12termite:visualization,
author = {Jason Chuang and Christopher D. Manning and Jeffrey Heer},
title = {Termite: Visualization techniques for assessing textual topic models},
booktitle = {In Proceedings of the International Working Conference on Advanced Visual Interfaces},
year = {2012},
pages = {74--77},
publisher = {ACM}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
Topic models aid analysis of text corpora by identifying la-tent topics based on co-occurring words. Real-world de-ployments of topic models, however, often require intensive expert verification and model refinement. In this paper we present Termite, a visual analysis tool for assessing topic model quality. Termite uses a tabular layout to promote comparison of terms both within and across latent topics. We contribute a novel saliency measure for selecting relevant terms and a seriation algorithm that both reveals clustering structure and promotes the legibility of related terms. In a series of examples, we demonstrate how Termite allows analysts to identify coherent and significant themes.
Keyphrases
textual topic model visualization technique topic model co-occurring word model refinement real-world de-ployments intensive expert verification significant theme tabular layout topic model quality text corpus relevant term novel saliency measure seriation algorithm latent topic present termite la-tent topic related term visual analysis tool
