Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Characterizing Uncertainty in the Visual Text Analysis Pipeline

Haghighatkhah, Pantea ; El-Assady, Mennatallah ; Fekete, Jean-Daniel ; Mahyar, Narges ; Paradis, Carita LU orcid ; Simaki, Vasiliki LU and Speckmann, Bettina (2022)
Abstract
Current visual text analysis approaches rely on sophisticated processing pipelines. Each step of such a pipeline potentially amplifies any uncertainties from the previous step. To ensure the comprehensibil- ity and interoperability of the results, it is of paramount importance to clearly communicate the uncertainty not only of the output but also within the pipeline. In this paper, we characterize the sources of uncertainty along the visual text analysis pipeline. Within its three phases of labeling, modeling, and analysis, we identify six sources, discuss the type of uncertainty they create, and how they propagate. The goal of this paper is to bring the attention of the visualization community to additional types and sources of... (More)
Current visual text analysis approaches rely on sophisticated processing pipelines. Each step of such a pipeline potentially amplifies any uncertainties from the previous step. To ensure the comprehensibil- ity and interoperability of the results, it is of paramount importance to clearly communicate the uncertainty not only of the output but also within the pipeline. In this paper, we characterize the sources of uncertainty along the visual text analysis pipeline. Within its three phases of labeling, modeling, and analysis, we identify six sources, discuss the type of uncertainty they create, and how they propagate. The goal of this paper is to bring the attention of the visualization community to additional types and sources of uncer- tainty in visual text analysis and to call for careful consideration, highlighting opportunities for future research. (Less)
Please use this url to cite or link to this publication:
author
; ; ; ; ; and
organization
publishing date
type
Working paper/Preprint
publication status
published
subject
keywords
Human-centered computing, Visualization, Visu- alization techniques, Treemaps, Visualization design and evaluation methods
pages
6 pages
publisher
arXiv.org
DOI
10.48550/arXiv.2209.13498
language
English
LU publication?
yes
additional info
To appear in Proceedings of the 2022 IEEE Workshop on Evaluation and Beyond - Methodological Approaches to Visualization (BELIV '22)
id
64e43eee-daea-4db7-a1f0-7c14349a0028
date added to LUP
2022-11-29 08:41:53
date last changed
2023-02-01 11:47:51
@misc{64e43eee-daea-4db7-a1f0-7c14349a0028,
  abstract     = {{Current visual text analysis approaches rely on sophisticated processing pipelines. Each step of such a pipeline potentially amplifies any  uncertainties from the previous step. To ensure the comprehensibil-  ity and interoperability of the results, it is of paramount importance  to clearly communicate the uncertainty not only of the output but  also within the pipeline. In this paper, we characterize the sources  of uncertainty along the visual text analysis pipeline. Within its  three phases of labeling, modeling, and analysis, we identify six  sources, discuss the type of uncertainty they create, and how they  propagate. The goal of this paper is to bring the attention of the  visualization community to additional types and sources of uncer-  tainty in visual text analysis and to call for careful consideration,  highlighting opportunities for future research.}},
  author       = {{Haghighatkhah, Pantea and El-Assady, Mennatallah and Fekete, Jean-Daniel and Mahyar, Narges and Paradis, Carita and Simaki, Vasiliki and Speckmann, Bettina}},
  keywords     = {{Human-centered computing; Visualization; Visu- alization techniques; Treemaps; Visualization design and evaluation methods}},
  language     = {{eng}},
  note         = {{Preprint}},
  publisher    = {{arXiv.org}},
  title        = {{Characterizing Uncertainty in the Visual Text Analysis Pipeline}},
  url          = {{http://dx.doi.org/10.48550/arXiv.2209.13498}},
  doi          = {{10.48550/arXiv.2209.13498}},
  year         = {{2022}},
}