Weighted argumentation for analysis of discussions in Twitter

被引:21
作者
Alsinet, Teresa [1 ]
Argelich, Josep [1 ]
Bejar, Ramon [1 ]
Fernandez, Cesar [1 ]
Mateu, Caries [1 ]
Planes, Jordi [1 ]
机构
[1] Univ Lleida, Dept Comp Sci, C Jaume 2 69, Lleida 25001, Spain
关键词
Abstract argumentation; Weighted arguments; Semantic attacks; Discussions in Twitter; SENTIMENT ANALYSIS; ALGORITHMS; EWOM;
D O I
10.1016/j.ijar.2017.02.004
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Twitter has become a widely used social network to discuss ideas about many domains. This leads to a growing interest in understanding what are the major accepted or rejected opinions in different domains by social network users. At the same time, checking what are the topics that produce the most controversial discussions among users can be a good tool to discover topics that can be divisive, what can be useful, e.g., for policy makers. With the aim to automatically discover such information from Twitter discussions, we present an analysis system based on Valued Abstract Argumentation to model and reason about the accepted and rejected opinions. We consider different schemes to weight the opinions of Twitter users, such that we can tune the relevance of opinions considering different information sources from the social network. Towards having a fully automatic system, we also design a relation labeling system for discovering the relation between opinions. Regarding the underlying acceptability semantics, we use ideal semantics to compute accepted rejected opinions. We define two measures over sets of accepted and rejected opinions to quantify the most controversial discussions. In order to validate our system, we analyze different real Twitter discussions from the political domain. The results show that different weighting schemes produce different sets of socially accepted opinions and that the controversy measures can reveal significant differences between discussions. (C) 2017 Elsevier Inc. All rights reserved.
引用
收藏
页码:21 / 35
页数:15
相关论文
共 50 条
[1]   RP-DeLP: a weighted defeasible argumentation framework based on a recursive semantics [J].
Alsinet, Teresa ;
Bejar, Ramon ;
Godo, Lluis ;
Guitart, Francesc .
JOURNAL OF LOGIC AND COMPUTATION, 2016, 26 (04) :1315-1360
[2]   Inferring from inconsistency in preference-based argumentation frameworks [J].
Amgoud, L ;
Cayrol, C .
JOURNAL OF AUTOMATED REASONING, 2002, 29 (02) :125-169
[3]   A reasoning model based on the production of acceptable arguments [J].
Amgoud, L ;
Cayrol, C .
ANNALS OF MATHEMATICS AND ARTIFICIAL INTELLIGENCE, 2002, 34 (1-3) :197-215
[4]  
[Anonymous], 2010, CORNELL HOSPITALITY
[5]  
[Anonymous], 1997, J. Appl. Non-class. Log., DOI DOI 10.1080/11663081.1997.10510900
[6]  
[Anonymous], 2013, P 14 INT C ART INT L
[7]  
[Anonymous], 2011, 22 INT JOINT C ARTIF
[8]  
[Anonymous], 2011, arXiv
[9]   PARMENIDES: Facilitating Deliberation in Democracies [J].
Atkinson, Katie ;
Bench-Capon, Trevor ;
Mcburney, Peter .
ARTIFICIAL INTELLIGENCE AND LAW, 2006, 14 (04) :261-275
[10]   Argumentation in artificial intelligence [J].
Bench-Capon, T. J. M. ;
Dunne, Paul E. .
ARTIFICIAL INTELLIGENCE, 2007, 171 (10-15) :619-641