Characterizing Uncertainty in the Visual Text Analysis Pipeline

Pantea Haghighatkhah; Mennatallah El-Assady; Jean-Daniel Fekete; Narges Mahyar; Carita Paradis; Vasiliki Simaki; Bettina Speckmann

doi:10.1109/VIS4DH57440.2022.00010

Characterizing Uncertainty in the Visual Text Analysis Pipeline

Pantea Haghighatkhah
, Mennatallah El-Assady
, Jean-Daniel Fekete
, Narges Mahyar
, Carita Paradis
, Vasiliki Simaki
, Bettina Speckmann

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

2 Citations (Scopus)

10 Downloads (Pure)

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 comprehensibility 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 uncertainty in visual text analysis and to call for careful consideration, highlighting opportunities for future research.

Original language	English
Title of host publication	2022 IEEE 7th Workshop on Visualization for the Digital Humanities, VIS4DH 2022
Publisher	Institute of Electrical and Electronics Engineers
Pages	25-30
Number of pages	6
ISBN (Electronic)	978-1-6654-7668-3
DOIs	https://doi.org/10.1109/VIS4DH57440.2022.00010
Publication status	Published - 12 Dec 2022
Event	7th Workshop on Visualization for the Digital Humanities, VIS4DH 2022 - Oklahoma City, United States Duration: 16 Oct 2022 → 16 Oct 2022

Conference

Conference	7th Workshop on Visualization for the Digital Humanities, VIS4DH 2022
Abbreviated title	VIS4DH 2022
Country/Territory	United States
City	Oklahoma City
Period	16/10/22 → 16/10/22

Keywords

Human-centered computing
Treemaps
Visualization
Visualization techniques

Access to Document

10.1109/VIS4DH57440.2022.00010

pdfFinal published version, 286 KBLicence: TAVERNE

Cite this

Haghighatkhah, P., El-Assady, M., Fekete, J.-D., Mahyar, N., Paradis, C., Simaki, V., & Speckmann, B. (2022). Characterizing Uncertainty in the Visual Text Analysis Pipeline. In 2022 IEEE 7th Workshop on Visualization for the Digital Humanities, VIS4DH 2022 (pp. 25-30). Article 9974768 Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/VIS4DH57440.2022.00010

@inproceedings{b3e1b687c7c24231b171d064dd16d2c3,

title = "Characterizing Uncertainty in the Visual Text Analysis Pipeline",

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 comprehensibility 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 uncertainty in visual text analysis and to call for careful consideration, highlighting opportunities for future research.",

keywords = "Human-centered computing, Treemaps, Visualization, Visualization techniques",

author = "Pantea Haghighatkhah and Mennatallah El-Assady and Jean-Daniel Fekete and Narges Mahyar and Carita Paradis and Vasiliki Simaki and Bettina Speckmann",

year = "2022",

month = dec,

day = "12",

doi = "10.1109/VIS4DH57440.2022.00010",

language = "English",

pages = "25--30",

booktitle = "2022 IEEE 7th Workshop on Visualization for the Digital Humanities, VIS4DH 2022",

publisher = "Institute of Electrical and Electronics Engineers",

address = "United States",

note = "7th Workshop on Visualization for the Digital Humanities, VIS4DH 2022, VIS4DH 2022 ; Conference date: 16-10-2022 Through 16-10-2022",

}

Haghighatkhah, P, El-Assady, M, Fekete, J-D, Mahyar, N, Paradis, C, Simaki, V & Speckmann, B 2022, Characterizing Uncertainty in the Visual Text Analysis Pipeline. in 2022 IEEE 7th Workshop on Visualization for the Digital Humanities, VIS4DH 2022., 9974768, Institute of Electrical and Electronics Engineers, pp. 25-30, 7th Workshop on Visualization for the Digital Humanities, VIS4DH 2022, Oklahoma City, United States, 16/10/22. https://doi.org/10.1109/VIS4DH57440.2022.00010

Characterizing Uncertainty in the Visual Text Analysis Pipeline. / Haghighatkhah, Pantea; El-Assady, Mennatallah; Fekete, Jean-Daniel et al.
2022 IEEE 7th Workshop on Visualization for the Digital Humanities, VIS4DH 2022. Institute of Electrical and Electronics Engineers, 2022. p. 25-30 9974768.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - Characterizing Uncertainty in the Visual Text Analysis Pipeline

AU - Haghighatkhah, Pantea

AU - El-Assady, Mennatallah

AU - Fekete, Jean-Daniel

AU - Mahyar, Narges

AU - Paradis, Carita

AU - Simaki, Vasiliki

AU - Speckmann, Bettina

PY - 2022/12/12

Y1 - 2022/12/12

N2 - 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 comprehensibility 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 uncertainty in visual text analysis and to call for careful consideration, highlighting opportunities for future research.

AB - 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 comprehensibility 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 uncertainty in visual text analysis and to call for careful consideration, highlighting opportunities for future research.

KW - Human-centered computing

KW - Treemaps

KW - Visualization

KW - Visualization techniques

UR - https://www.scopus.com/pages/publications/85145661877

U2 - 10.1109/VIS4DH57440.2022.00010

DO - 10.1109/VIS4DH57440.2022.00010

M3 - Conference contribution

SP - 25

EP - 30

BT - 2022 IEEE 7th Workshop on Visualization for the Digital Humanities, VIS4DH 2022

PB - Institute of Electrical and Electronics Engineers

T2 - 7th Workshop on Visualization for the Digital Humanities, VIS4DH 2022

Y2 - 16 October 2022 through 16 October 2022

ER -

Characterizing Uncertainty in the Visual Text Analysis Pipeline

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this