Towards modelling dialectic and eristic argumentation on the social web
Towards modelling dialectic and eristic argumentation on the social web
Modelling arguments on the social web is a key challenge for those studying computational argumentation. This is because formal models of argumentation tend to assume dialectic and logical argument, whereas argumentation on the social web is highly eristic. In this paper we explore this gap by bringing together the Argument Interchange Format (AIF) and the Semantic Interlinked Online Communities (SIOC) project, and modelling a sample of social web arguments. This allows us to explore which eristic effects cannot be modelled, and also to see which features of the social web are missing.We show that even in our small sample, from YouTube, Twitter and Facebook, eristic effects (such as playing to the audience) were missing from the final model, and that key social features (such as likes and dislikes) were also not represented. This suggests that both eristic and social extensions need to be made to our models of argumentation in order to deal effectively with the social web
Blount, Thomas
7c4e5a1d-d105-4c18-8f02-42bd65e3f3a7
Millard, David
4f19bca5-80dc-4533-a101-89a5a0e3b372
Weal, Mark
e8fd30a6-c060-41c5-b388-ca52c81032a4
10 December 2014
Blount, Thomas
7c4e5a1d-d105-4c18-8f02-42bd65e3f3a7
Millard, David
4f19bca5-80dc-4533-a101-89a5a0e3b372
Weal, Mark
e8fd30a6-c060-41c5-b388-ca52c81032a4
Blount, Thomas, Millard, David and Weal, Mark
(2014)
Towards modelling dialectic and eristic argumentation on the social web.
14th Workshop on Computational Models of Natural Argument, Krakow, Poland.
5 pp
.
Record type:
Conference or Workshop Item
(Paper)
Abstract
Modelling arguments on the social web is a key challenge for those studying computational argumentation. This is because formal models of argumentation tend to assume dialectic and logical argument, whereas argumentation on the social web is highly eristic. In this paper we explore this gap by bringing together the Argument Interchange Format (AIF) and the Semantic Interlinked Online Communities (SIOC) project, and modelling a sample of social web arguments. This allows us to explore which eristic effects cannot be modelled, and also to see which features of the social web are missing.We show that even in our small sample, from YouTube, Twitter and Facebook, eristic effects (such as playing to the audience) were missing from the final model, and that key social features (such as likes and dislikes) were also not represented. This suggests that both eristic and social extensions need to be made to our models of argumentation in order to deal effectively with the social web
Text
argumentation.pdf
- Accepted Manuscript
More information
Submitted date: 31 October 2014
Published date: 10 December 2014
Venue - Dates:
14th Workshop on Computational Models of Natural Argument, Krakow, Poland, 2014-12-10
Organisations:
Web & Internet Science
Identifiers
Local EPrints ID: 372090
URI: http://eprints.soton.ac.uk/id/eprint/372090
PURE UUID: 1f26a532-1ea4-41be-9cd6-1d1adfac34b1
Catalogue record
Date deposited: 27 Nov 2014 13:06
Last modified: 15 Mar 2024 02:59
Export record
Contributors
Author:
Thomas Blount
Author:
David Millard
Author:
Mark Weal
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics