Weighted argumentation for analysis of discussions in Twitter

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.

[1]  Ana Gabriela Maguitman,et al.  Integrating argumentation and sentiment analysis for mining opinions from Twitter , 2015, AI Commun..

[2]  Guillermo Ricardo Simari,et al.  Defeasible logic programming: an argumentative approach , 2003, Theory and Practice of Logic Programming.

[3]  Claudette Cayrol,et al.  Graduality in Argumentation , 2011, J. Artif. Intell. Res..

[4]  Finn Årup Nielsen,et al.  A New ANEW: Evaluation of a Word List for Sentiment Analysis in Microblogs , 2011, #MSM.

[5]  Henry Prakken,et al.  Argument-Based Extended Logic Programming with Defeasible Priorities , 1997, J. Appl. Non Class. Logics.

[6]  Claudette Cayrol,et al.  A Reasoning Model Based on the Production of Acceptable Arguments , 2002, Annals of Mathematics and Artificial Intelligence.

[7]  Phan Minh Dung,et al.  On the Acceptability of Arguments and its Fundamental Role in Nonmonotonic Reasoning, Logic Programming and n-Person Games , 1995, Artif. Intell..

[8]  Bernard J. Jansen,et al.  Business engagement on Twitter: a path analysis , 2011, Electron. Mark..

[9]  Giuseppe Porro,et al.  Every tweet counts? How sentiment analysis of social media can improve our knowledge of citizens’ political preferences with an application to Italy and France , 2013, New Media Soc..

[10]  Guillermo Ricardo Simari,et al.  Argumentation in Artificial Intelligence , 2009 .

[11]  Paul E. Dunne,et al.  The Computational Complexity of Ideal Semantics I: Abstract Argumentation Frameworks , 2008, COMMA.

[12]  Katie Atkinson,et al.  Using Computational Argumentation to Support E-participation , 2009, IEEE Intelligent Systems.

[13]  R. Procter,et al.  Reading the riots on Twitter: methodological innovation for the analysis of big data , 2013 .

[14]  Wolfgang Faber,et al.  Manifold Answer-Set Programs for Meta-reasoning , 2009, LPNMR.

[15]  Isabell M. Welpe,et al.  Predicting Elections with Twitter: What 140 Characters Reveal about Political Sentiment , 2010, ICWSM.

[16]  Rohit Verma,et al.  How Travelers Use Online and Social Media Channels to Make Hotel-choice Decisions , 2010 .

[17]  Michael Zimmer,et al.  A topology of Twitter research: disciplines, methods, and ethics , 2014, Aslib J. Inf. Manag..

[18]  Michael Wooldridge,et al.  Weighted argument systems: Basic definitions, algorithms, and complexity results , 2011, Artif. Intell..

[19]  Paul E. Dunnea,et al.  Parametric properties of ideal semantics , 2013 .

[20]  Lars Kai Hansen,et al.  Good Friends, Bad News - Affect and Virality in Twitter , 2011, ArXiv.

[21]  Matteo Negri,et al.  An Open-Source Package for Recognizing Textual Entailment , 2010, ACL.

[22]  Paolo Mancarella,et al.  Computing ideal sceptical argumentation , 2007, Artif. Intell..

[23]  Paul-Amaury Matt,et al.  A Game-Theoretic Measure of Argument Strength for Abstract Argumentation , 2008, JELIA.

[24]  Trevor J. M. Bench-Capon,et al.  PARMENIDES: Facilitating Deliberation in Democracies , 2006, Artificial Intelligence and Law.

[25]  Trevor J. M. Bench-Capon.  Value-based argumentation frameworks , 2002, NMR.

[26]  Wolfgang Dvorák,et al.  dynPARTIX 2.0 - Dynamic Programming Argumentation Reasoning Tool , 2012, COMMA.

[27]  Steven Bird,et al.  NLTK: The Natural Language Toolkit , 2002, ACL.

[28]  Daniel Villatoro,et al.  The TweetBeat of the City: Microblogging Used for Discovering Behavioural Patterns during the MWC2012 , 2012, CitiSens.

[29]  Serena Villata,et al.  A natural language bipolar argumentation approach to support users in online debate interactions† , 2013, Argument Comput..

[30]  Claire Grover,et al.  Re-using an Argument Corpus to Aid in the Curation of Social Media Collections , 2014, LREC.

[31]  João Leite,et al.  Social Abstract Argumentation , 2011, IJCAI.

[32]  Shu-Chuan Chu,et al.  Determinants of consumer engagement in electronic word-of-mouth (eWOM) in social networking sites , 2011 .

[33]  Bernard J. Jansen,et al.  Twitter power: Tweets as electronic word of mouth , 2009, J. Assoc. Inf. Sci. Technol..

[34]  Suzan Burton,et al.  Interactive or reactive? : marketing with Twitter , 2011 .

[35]  Paul E. Dunne,et al.  The computational complexity of ideal semantics , 2009, Artif. Intell..

[36]  Tom M. van Engers,et al.  Working on the argument pipeline: Through flow issues between natural language argument, instantiated arguments, and argumentation frameworks , 2016, Argument Comput..

[37]  Stefan Woltran,et al.  Towards fixed-parameter tractable algorithms for abstract argumentation , 2012, Artif. Intell..

[38]  Ana Gabriela Maguitman,et al.  An Argument-based Approach to Mining Opinions from Twitter , 2012, AT.

[39]  Trevor J. M. Bench-Capon.  Persuasion in Practical Argument Using Value-based Argumentation Frameworks , 2003, J. Log. Comput..

[40]  Paul E. Dunne,et al.  Computational properties of argument systems satisfying graph-theoretic constraints , 2007, Artif. Intell..

[41]  Dimitrios Buhalis,et al.  Community crosstalk: an exploratory analysis of destination and festival eWOM on Twitter , 2015 .

[42]  Teresa Alsinet,et al.  RP-DeLP: a weighted defeasible argumentation framework based on a recursive semantics , 2016, J. Log. Comput..

[43]  Trevor J. M. Bench-Capon,et al.  Argumentation in artificial intelligence , 2007, Artif. Intell..

[44]  Sanjay Modgil,et al.  Reasoning about preferences in argumentation frameworks , 2009, Artif. Intell..

[45]  Stefan Woltran,et al.  ASPARTIX: Implementing Argumentation Frameworks Using Answer-Set Programming , 2008, ICLP.

[46]  Katie Atkinson,et al.  Political Engagement Through Tools for Argumentation , 2008, COMMA.

[47]  Claudette Cayrol,et al.  Inferring from Inconsistency in Preference-Based Argumentation Frameworks , 2002, Journal of Automated Reasoning.

[48]  João Leite,et al.  Extending Social Abstract Argumentation with Votes on Attacks , 2013, TAFA.

[49]  Bernard J. Jansen,et al.  Twitter power: Tweets as electronic word of mouth , 2009 .

[50]  Trevor J. M. Bench-Capon,et al.  Argumentation based tools for policy-making , 2013, ICAIL.