Interactive Concept Learning for Uncovering Latent Themes in Large Text Collections

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Pacheco, Maria Leonor, Islam, Tunazzina, Ungar, Lyle, Yin, Ming, Goldwasser, Dan
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914982384369664
author Pacheco, Maria Leonor
Islam, Tunazzina
Ungar, Lyle
Yin, Ming
Goldwasser, Dan
author_facet Pacheco, Maria Leonor
Islam, Tunazzina
Ungar, Lyle
Yin, Ming
Goldwasser, Dan
contents Experts across diverse disciplines are often interested in making sense of large text collections. Traditionally, this challenge is approached either by noisy unsupervised techniques such as topic models, or by following a manual theme discovery process. In this paper, we expand the definition of a theme to account for more than just a word distribution, and include generalized concepts deemed relevant by domain experts. Then, we propose an interactive framework that receives and encodes expert feedback at different levels of abstraction. Our framework strikes a balance between automation and manual coding, allowing experts to maintain control of their study while reducing the manual effort required.
format Preprint
id arxiv_https___arxiv_org_abs_2305_05094
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Interactive Concept Learning for Uncovering Latent Themes in Large Text Collections
Pacheco, Maria Leonor
Islam, Tunazzina
Ungar, Lyle
Yin, Ming
Goldwasser, Dan
Computation and Language
Human-Computer Interaction
Experts across diverse disciplines are often interested in making sense of large text collections. Traditionally, this challenge is approached either by noisy unsupervised techniques such as topic models, or by following a manual theme discovery process. In this paper, we expand the definition of a theme to account for more than just a word distribution, and include generalized concepts deemed relevant by domain experts. Then, we propose an interactive framework that receives and encodes expert feedback at different levels of abstraction. Our framework strikes a balance between automation and manual coding, allowing experts to maintain control of their study while reducing the manual effort required.
title Interactive Concept Learning for Uncovering Latent Themes in Large Text Collections
topic Computation and Language
Human-Computer Interaction
url https://arxiv.org/abs/2305.05094