Visualization of the Topic Space of Argument Search Results in args.me

Publikation: Beitrag in Buch/Bericht/Sammelwerk/KonferenzbandAufsatz in KonferenzbandForschungPeer-Review

Autoren

Externe Organisationen

  • Bauhaus-Universität Weimar
  • Universität Paderborn
Forschungs-netzwerk anzeigen

Details

OriginalspracheEnglisch
Titel des SammelwerksProceedings of the 2018 Conference on Empirical Methods in Natural Language Processing (System Demonstrations)
Herausgeber/-innenEduardo Blanco, Wei Lu
ErscheinungsortBrüssel
Seiten60-65
Seitenumfang6
PublikationsstatusVeröffentlicht - Nov. 2018
Extern publiziertJa
Veranstaltung2018 Conference on Empirical Methods in Natural Language Processing - Brüssel, Belgien
Dauer: 31 Okt. 20184 Nov. 2018

Abstract

In times of fake news and alternative facts, pro and con arguments on controversial topics are of increasing importance. Recently, we presented args.me as the first search engine for arguments on the web. In its initial version, args.me ranked arguments solely by their relevance to a topic queried for, making it hard to learn about the diverse topical aspects covered by the search results. To tackle this shortcoming, we integrated a visualization interface for result exploration in args.me that provides an instant overview of the main aspects in a barycentric coordinate system. This topic space is generated ad-hoc from controversial issues on Wikipedia and argument-specific LDA models. In two case studies, we demonstrate how individual arguments can be found easily through interactions with the visualization, such as highlighting and filtering.

ASJC Scopus Sachgebiete

Zitieren

Visualization of the Topic Space of Argument Search Results in args.me. / Ajjour, Yamen; Wachsmuth, Henning; Kiesel, Dora et al.
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing (System Demonstrations). Hrsg. / Eduardo Blanco; Wei Lu. Brüssel, 2018. S. 60-65.

Publikation: Beitrag in Buch/Bericht/Sammelwerk/KonferenzbandAufsatz in KonferenzbandForschungPeer-Review

Ajjour, Y, Wachsmuth, H, Kiesel, D, Riehmann, P, Fan, F, Castiglia, G, Adejoh, R, Fröhlich, B & Stein, B 2018, Visualization of the Topic Space of Argument Search Results in args.me. in E Blanco & W Lu (Hrsg.), Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing (System Demonstrations). Brüssel, S. 60-65, 2018 Conference on Empirical Methods in Natural Language Processing, Brüssel, Belgien, 31 Okt. 2018. https://doi.org/10.18653/v1/d18-2011
Ajjour, Y., Wachsmuth, H., Kiesel, D., Riehmann, P., Fan, F., Castiglia, G., Adejoh, R., Fröhlich, B., & Stein, B. (2018). Visualization of the Topic Space of Argument Search Results in args.me. In E. Blanco, & W. Lu (Hrsg.), Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing (System Demonstrations) (S. 60-65). https://doi.org/10.18653/v1/d18-2011
Ajjour Y, Wachsmuth H, Kiesel D, Riehmann P, Fan F, Castiglia G et al. Visualization of the Topic Space of Argument Search Results in args.me. in Blanco E, Lu W, Hrsg., Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing (System Demonstrations). Brüssel. 2018. S. 60-65 doi: 10.18653/v1/d18-2011
Ajjour, Yamen ; Wachsmuth, Henning ; Kiesel, Dora et al. / Visualization of the Topic Space of Argument Search Results in args.me. Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing (System Demonstrations). Hrsg. / Eduardo Blanco ; Wei Lu. Brüssel, 2018. S. 60-65
Download
@inproceedings{0f9ed6bce4244eb8b416812cc4792e3c,
title = "Visualization of the Topic Space of Argument Search Results in args.me",
abstract = "In times of fake news and alternative facts, pro and con arguments on controversial topics are of increasing importance. Recently, we presented args.me as the first search engine for arguments on the web. In its initial version, args.me ranked arguments solely by their relevance to a topic queried for, making it hard to learn about the diverse topical aspects covered by the search results. To tackle this shortcoming, we integrated a visualization interface for result exploration in args.me that provides an instant overview of the main aspects in a barycentric coordinate system. This topic space is generated ad-hoc from controversial issues on Wikipedia and argument-specific LDA models. In two case studies, we demonstrate how individual arguments can be found easily through interactions with the visualization, such as highlighting and filtering.",
author = "Yamen Ajjour and Henning Wachsmuth and Dora Kiesel and Patrick Riehmann and Fan Fan and Giuliano Castiglia and Rosemary Adejoh and Bernd Fr{\"o}hlich and Benno Stein",
year = "2018",
month = nov,
doi = "10.18653/v1/d18-2011",
language = "English",
isbn = "9781948087858",
pages = "60--65",
editor = "Eduardo Blanco and Wei Lu",
booktitle = "Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing (System Demonstrations)",
note = "2018 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, EMNLP 2018 ; Conference date: 31-10-2018 Through 04-11-2018",

}

Download

TY - GEN

T1 - Visualization of the Topic Space of Argument Search Results in args.me

AU - Ajjour, Yamen

AU - Wachsmuth, Henning

AU - Kiesel, Dora

AU - Riehmann, Patrick

AU - Fan, Fan

AU - Castiglia, Giuliano

AU - Adejoh, Rosemary

AU - Fröhlich, Bernd

AU - Stein, Benno

PY - 2018/11

Y1 - 2018/11

N2 - In times of fake news and alternative facts, pro and con arguments on controversial topics are of increasing importance. Recently, we presented args.me as the first search engine for arguments on the web. In its initial version, args.me ranked arguments solely by their relevance to a topic queried for, making it hard to learn about the diverse topical aspects covered by the search results. To tackle this shortcoming, we integrated a visualization interface for result exploration in args.me that provides an instant overview of the main aspects in a barycentric coordinate system. This topic space is generated ad-hoc from controversial issues on Wikipedia and argument-specific LDA models. In two case studies, we demonstrate how individual arguments can be found easily through interactions with the visualization, such as highlighting and filtering.

AB - In times of fake news and alternative facts, pro and con arguments on controversial topics are of increasing importance. Recently, we presented args.me as the first search engine for arguments on the web. In its initial version, args.me ranked arguments solely by their relevance to a topic queried for, making it hard to learn about the diverse topical aspects covered by the search results. To tackle this shortcoming, we integrated a visualization interface for result exploration in args.me that provides an instant overview of the main aspects in a barycentric coordinate system. This topic space is generated ad-hoc from controversial issues on Wikipedia and argument-specific LDA models. In two case studies, we demonstrate how individual arguments can be found easily through interactions with the visualization, such as highlighting and filtering.

UR - http://www.scopus.com/inward/record.url?scp=85072974709&partnerID=8YFLogxK

U2 - 10.18653/v1/d18-2011

DO - 10.18653/v1/d18-2011

M3 - Conference contribution

AN - SCOPUS:85072974709

SN - 9781948087858

SP - 60

EP - 65

BT - Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing (System Demonstrations)

A2 - Blanco, Eduardo

A2 - Lu, Wei

CY - Brüssel

T2 - 2018 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, EMNLP 2018

Y2 - 31 October 2018 through 4 November 2018

ER -

Von denselben Autoren