Interactive visualization for topic model curation

Guoray Cai, Feng Sun, Yongzhong Sha

Research output: Contribution to journalConference article

Abstract

Understanding the content of a large text corpus can be assisted by topic modeling methods, but the discovered topics often do not make clear sense to human analysts. Interactive topic modeling addresses such problems by allowing a human to steer the topic model curation process (generate, interpret, diagnose, and refine). However, human have limited ability to work with the artifacts of computational topic models since they are difficult to interpret and harvest. This paper explores the nature of such challenges and provides a visual analytic solution in the context of supporting political scientists to understand the thematic content of online petition data. We use interactive topic modeling of the White House online petition data as a lens to bring up key points of discussions and to highlight the unsolved problems as well as potentials utilities of visual analytics methods.

Original languageEnglish (US)
JournalCEUR Workshop Proceedings
Volume2068
StatePublished - Jan 1 2018
Event2018 Joint ACM IUI Workshops, ACMIUI-WS 2018 - Tokyo, Japan
Duration: Mar 11 2018 → …

Fingerprint

Visualization
Lenses

All Science Journal Classification (ASJC) codes

  • Computer Science(all)

Cite this

Cai, Guoray ; Sun, Feng ; Sha, Yongzhong. / Interactive visualization for topic model curation. In: CEUR Workshop Proceedings. 2018 ; Vol. 2068.
@article{b4795fb9d9584722a35a26ed5ec386b8,
title = "Interactive visualization for topic model curation",
abstract = "Understanding the content of a large text corpus can be assisted by topic modeling methods, but the discovered topics often do not make clear sense to human analysts. Interactive topic modeling addresses such problems by allowing a human to steer the topic model curation process (generate, interpret, diagnose, and refine). However, human have limited ability to work with the artifacts of computational topic models since they are difficult to interpret and harvest. This paper explores the nature of such challenges and provides a visual analytic solution in the context of supporting political scientists to understand the thematic content of online petition data. We use interactive topic modeling of the White House online petition data as a lens to bring up key points of discussions and to highlight the unsolved problems as well as potentials utilities of visual analytics methods.",
author = "Guoray Cai and Feng Sun and Yongzhong Sha",
year = "2018",
month = "1",
day = "1",
language = "English (US)",
volume = "2068",
journal = "CEUR Workshop Proceedings",
issn = "1613-0073",
publisher = "CEUR-WS",

}

Interactive visualization for topic model curation. / Cai, Guoray; Sun, Feng; Sha, Yongzhong.

In: CEUR Workshop Proceedings, Vol. 2068, 01.01.2018.

Research output: Contribution to journalConference article

TY - JOUR

T1 - Interactive visualization for topic model curation

AU - Cai, Guoray

AU - Sun, Feng

AU - Sha, Yongzhong

PY - 2018/1/1

Y1 - 2018/1/1

N2 - Understanding the content of a large text corpus can be assisted by topic modeling methods, but the discovered topics often do not make clear sense to human analysts. Interactive topic modeling addresses such problems by allowing a human to steer the topic model curation process (generate, interpret, diagnose, and refine). However, human have limited ability to work with the artifacts of computational topic models since they are difficult to interpret and harvest. This paper explores the nature of such challenges and provides a visual analytic solution in the context of supporting political scientists to understand the thematic content of online petition data. We use interactive topic modeling of the White House online petition data as a lens to bring up key points of discussions and to highlight the unsolved problems as well as potentials utilities of visual analytics methods.

AB - Understanding the content of a large text corpus can be assisted by topic modeling methods, but the discovered topics often do not make clear sense to human analysts. Interactive topic modeling addresses such problems by allowing a human to steer the topic model curation process (generate, interpret, diagnose, and refine). However, human have limited ability to work with the artifacts of computational topic models since they are difficult to interpret and harvest. This paper explores the nature of such challenges and provides a visual analytic solution in the context of supporting political scientists to understand the thematic content of online petition data. We use interactive topic modeling of the White House online petition data as a lens to bring up key points of discussions and to highlight the unsolved problems as well as potentials utilities of visual analytics methods.

UR - http://www.scopus.com/inward/record.url?scp=85044529787&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85044529787&partnerID=8YFLogxK

M3 - Conference article

AN - SCOPUS:85044529787

VL - 2068

JO - CEUR Workshop Proceedings

JF - CEUR Workshop Proceedings

SN - 1613-0073

ER -