Details
Originalsprache | Englisch |
---|---|
Titel des Sammelwerks | Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing |
Seiten | 1351-1357 |
Seitenumfang | 7 |
Publikationsstatus | Veröffentlicht - Aug. 2017 |
Extern publiziert | Ja |
Veranstaltung | 2017 Conference on Empirical Methods in Natural Language Processing - Copenhagen, Dänemark Dauer: 7 Sept. 2017 → 11 Sept. 2017 |
Abstract
This paper presents an analysis of argumentation strategies in news editorials within and across topics. Given nearly 29,000 argumentative editorials from the New York Times, we develop two machine learning models, one for determining an editorial’s topic, and one for identifying evidence types in the editorial. Based on the distribution and structure of the identified types, we analyze the usage patterns of argumentation strategies among 12 different topics. We detect several common patterns that provide insights into the manifestation of argumentation strategies. Also, our experiments reveal clear correlations between the topics and the detected patterns.
ASJC Scopus Sachgebiete
- Informatik (insg.)
- Angewandte Informatik
- Informatik (insg.)
- Information systems
- Informatik (insg.)
- Theoretische Informatik und Mathematik
Zitieren
- Standard
- Harvard
- Apa
- Vancouver
- BibTex
- RIS
Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing. 2017. S. 1351-1357.
Publikation: Beitrag in Buch/Bericht/Sammelwerk/Konferenzband › Aufsatz in Konferenzband › Forschung › Peer-Review
}
TY - GEN
T1 - Patterns of Argumentation Strategies across Topics
AU - Al-Khatib, Khalid
AU - Wachsmuth, Henning
AU - Hagen, Matthias
AU - Stein, Benno
PY - 2017/8
Y1 - 2017/8
N2 - This paper presents an analysis of argumentation strategies in news editorials within and across topics. Given nearly 29,000 argumentative editorials from the New York Times, we develop two machine learning models, one for determining an editorial’s topic, and one for identifying evidence types in the editorial. Based on the distribution and structure of the identified types, we analyze the usage patterns of argumentation strategies among 12 different topics. We detect several common patterns that provide insights into the manifestation of argumentation strategies. Also, our experiments reveal clear correlations between the topics and the detected patterns.
AB - This paper presents an analysis of argumentation strategies in news editorials within and across topics. Given nearly 29,000 argumentative editorials from the New York Times, we develop two machine learning models, one for determining an editorial’s topic, and one for identifying evidence types in the editorial. Based on the distribution and structure of the identified types, we analyze the usage patterns of argumentation strategies among 12 different topics. We detect several common patterns that provide insights into the manifestation of argumentation strategies. Also, our experiments reveal clear correlations between the topics and the detected patterns.
UR - http://www.scopus.com/inward/record.url?scp=85061320727&partnerID=8YFLogxK
U2 - 10.18653/v1/d17-1141
DO - 10.18653/v1/d17-1141
M3 - Conference contribution
AN - SCOPUS:85061320727
SN - 9781945626838
SP - 1351
EP - 1357
BT - Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing
T2 - 2017 Conference on Empirical Methods in Natural Language Processing, EMNLP 2017
Y2 - 7 September 2017 through 11 September 2017
ER -