Skip to main content
SpringerLink
Log in

A distributed argumentation algorithm for mining consistent opinions in weighted Twitter discussions

  • Focus
  • Published:
Soft Computing Aims and scope Submit manuscript

Abstract

Twitter is one of the most powerful social media platforms, reflecting both support and contrary opinions among people who use it. In a recent work, we developed an argumentative approach for analyzing the major opinions accepted and rejected in Twitter discussions. A Twitter discussion is modeled as a weighted argumentation graph where each node denotes a tweet, each edge denotes a relationship between a pair of tweets of the discussion and each node is attached to a weight that denotes the social relevance of the corresponding tweet in the discussion. In the social network Twitter, a tweet always refers to previous tweets in the discussion, and therefore the underlying argument graph obtained is acyclic. However, when in a discussion we group the tweets by author, the graph that we obtain can contain cycles. Based on the structure of graphs, in this work we introduce a distributed algorithm to compute the set of globally accepted opinions of a Twitter discussion based on valued argumentation. To understand the usefulness of our distributed algorithm, we study cases of argumentation graphs that can be solved efficiently with it. Finally, we present an experimental investigation that shows that when solving acyclic argumentation graphs associated with Twitter discussions our algorithm scales at most with linear time with respect to the size of the discussion. For argumentation graphs with cycles, we study tractable cases and we analyze how frequent are these cases in Twitter. Moreover, for the non-tractable cases we analyze how close is the solution of the distributed algorithm with respect to the one computed with the general sequential algorithm, that we have previously developed, that solves any argumentation graph.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7

Similar content being viewed by others

Notes

  1. Following the URLs you can access the original tweets. At the time of writing this article the author of the root node was deleted, so the Tweet 0 is not accessible anymore. In the following link you can get the full conversation used for the example in XML format: http://ia.udl.cat/remository/func-startdown/23/.

  2. The pseudocode is written using object-oriented notation, as the Pregel API is written in C++. However, our actual implementation is based on the Pregel implementation found in the Spark distributed programming framework, graphX, which is written in Scala.

  3. A bipartite graph (or bigraph) is a graph whose nodes can be divided into two disjoint sets such that no two graph nodes within the same set are adjacent.

  4. Since both Defeats Graphs and Author’s Defeats Graph are directed graphs, it may occur that an argumentation graph does not contain cycles but it is not bipartite. In this case, we can also use the distributed Algorithm 4.1 to compute its solution.

  5. All the conversations were sampled from the results obtained when searching for tweets with the hashtag #PedroSanchez.

  6. We do not have available a polynomial time algorithm for checking whether a directed graph has even cycles, so we have not checked if there were any no even cycle graphs.

References

  • Alsinet T, Argelich J, Béjar R, Esteva F, Godo L (2017a) A probabilistic author-centered model for Twitter discussions. In: IJCAI workshop on logical foundations for uncertainty and machine learning, pp 3–8

  • Alsinet T, Argelich J, Béjar R, Fernández C, Mateu C, Planes J (2017b) Weighted argumentation for analysis of discussions in Twitter. Int J Approx Reason 85:21–35

    Article  MathSciNet  MATH  Google Scholar 

  • Alsinet T, Argelich J, Béjar R, Planes J, Cemeli J, Sanahuja C (2017c) A distributed approach for the analysis of discussions in twitter. In: Proceedings of the 3rd international workshop on social influence analysis co-located with 26th international joint conference on artificial intelligence (IJCAI 2017), Melbourne, Australia, August 19, 2017, pp 45–56

  • Alsinet T, Argelich J, Béjar R, Fernández C, Mateu C, Planes J (2018) An argumentative approach for discovering relevant opinions in Twitter with probabilistic valued relationships. Pattern Recogn Lett 105:191–199. https://doi.org/10.1016/j.patrec.2017.07.004

    Article  Google Scholar 

  • Baroni P, Giacomin M (2001) A distributed self-stabilizing algorithm for argumentation. In: Proceedings of the 15th international parallel and distributed processing symposium (IPDPS-01), IEEE Computer Society, p 79

  • Baroni P, Giacomin M (2002) Argumentation through a distributed self-stabilizing approach. J Exp Theor Artif Intell 14(4):273–301

    Article  MATH  Google Scholar 

  • Bench-Capon TJM (2002) Value-based argumentation frameworks. In: Proceedings of 9th international workshop on non-monotonic reasoning, NMR 2002, pp 443–454

  • Bench-Capon TJM (2003) Persuasion in practical argument using value-based argumentation frameworks. J Log Comput 13(3):429–448

    Article  MathSciNet  MATH  Google Scholar 

  • Bench-Capon TJM, Dunne PE (2007) Argumentation in artificial intelligence. Artif Intell 171(10–15):619–641

    Article  MathSciNet  MATH  Google Scholar 

  • Besnard P, Hunter A (2001) A logic-based theory of deductive arguments. Artif Intell 128(1–2):203–235

    Article  MathSciNet  MATH  Google Scholar 

  • Bild DR, Liu Y, Dick RP, Mao ZM, Wallach DS (2015) Aggregate characterization of user behavior in Twitter and analysis of the retweet graph. ACM Trans Internet Technol 15(1):41–424

    Article  Google Scholar 

  • Bosc T, Cabrio E, Villata S (2016) Tweeties squabbling: positive and negative results in applying argument mining on social media. Comput Models Argum–Proc COMMA 2016:21–32

    Google Scholar 

  • Budán MCD, Simari GI, Simari GR (2016) Using argument features to improve the argumentation process. In: Proceedings of COMMA 2016 Computational Models of Argument, Potsdam, Germany, 12-16 September, 2016, pp 151–158

  • Caminada M (2007) Comparing two unique extension semantics for formal argumentation: ideal and eager. In: Proceedings of 19th Belgian–Dutch conference on artificial intelligence (BNAIC 2007), pp 81–87

  • Dung PM (1995) On the acceptability of arguments and its fundamental role in nonmonotonic reasoning, logic programming and n-person games. Artif Intell 77(2):321–357

    Article  MathSciNet  MATH  Google Scholar 

  • Dung PM, Mancarella P, Toni F (2007) Computing ideal sceptical argumentation. Artif Intell 171(10–15):642–674

    Article  MathSciNet  MATH  Google Scholar 

  • Dunne PE (2007) Computational properties of argument systems satisfying graph-theoretic constraints. Artif Intell 171(10–15):701–729

    Article  MathSciNet  MATH  Google Scholar 

  • Dunne PE (2008) The computational complexity of ideal semantics I: abstract argumentation frameworks. In: Proceedings of computational models of argument, COMMA 2008, Toulouse, France, pp 147–158

  • Dunne PE (2009) The computational complexity of ideal semantics. Artif Intell 173(18):1559–1591

    Article  MathSciNet  MATH  Google Scholar 

  • Dunne PE, Bench-Capon T (2001) Complexity and combinatorial properties of argument systems. Tech. rep., University of Liverpool. http://www.csc.liv.ac.uk/~ped/papers/csd_rep_argument.ps

  • Dusmanu M, Cabrio E, Villata S (2017) Argument mining on twitter: arguments, facts and sources. In: Proceedings of the 2017 conference on empirical methods in natural language processing, EMNLP 2017, pp 2317–2322

  • Dvorák W, Ordyniak S, Szeider S (2012) Augmenting tractable fragments of abstract argumentation. Artif Intell 186:157–173. https://doi.org/10.1016/j.artint.2012.03.002

    Article  MathSciNet  MATH  Google Scholar 

  • Egly U, Gaggl SA, Woltran S (2008) Aspartix: implementing argumentation frameworks using answer-set programming. In: Proceedings of the 24th international conference on logic programming, ICLP 2008, pp 734–738

  • Fazzinga B, Flesca S, Parisi F (2013) On the complexity of probabilistic abstract argumentation. In: IJCAI 2013, Proceedings of the 23rd international joint conference on artificial intelligence, pp 898–904. IJCAI/AAAI

  • Grosse K, Chesñevar CI, Maguitman AG (2012) An argument-based approach to mining opinions from Twitter. In: Proceedings of the first international conference on agreement technologies, AT 2012, CEUR Workshop Proceedings, vol 918, pp 408–422. CEUR-WS.org

  • Grosse K, González MP, Chesñevar CI, Maguitman AG (2015) Integrating argumentation and sentiment analysis for mining opinions from Twitter. AI Commun 28(3):387–401

    Article  MathSciNet  MATH  Google Scholar 

  • Hunter A (2012) Some foundations for probabilistic abstract argumentation. In: Computational Models of Argument–Proceedings of COMMA 2012, Frontiers in Artificial Intelligence and Applications, vol 245, pp 117–128. IOS Press

  • Hunter A (2014) Probabilistic qualification of attack in abstract argumentation. Int J Approx Reason 55(2):607–638

    Article  MathSciNet  MATH  Google Scholar 

  • Li H, Oren N, Norman TJ (2011) Probabilistic argumentation frameworks. In: Theory and applications of formal argumentation–first international workshop, TAFA 2011, Lecture Notes in Computer Science, vol 7132, pp 1–16. Springer, Berlin

  • Malewicz G, Austern MH, Bik AJC, Dehnert JC, Horn I, Leiser N, Czajkowski G (2010) Pregel: a system for large-scale graph processing. In: Proceedings of the ACM SIGMOD international conference on management of data, SIGMOD 2010, pp 135–146

  • Rahwan I, Simari GR (2009) Argumentation in artificial intelligence, 1st edn. Springer Publishing Company, Berlin

    Google Scholar 

  • Thimm M (2012) A probabilistic semantics for abstract argumentation. In: ECAI 2012–20th European conference on artificial intelligence, frontiers in artificial intelligence and applications, vol 242, pp 750–755. IOS Press

  • Valiant LG (2011) A bridging model for multi-core computing. J Comput Syst Sci 77(1):154–166

    Article  MathSciNet  MATH  Google Scholar 

Download references

Funding

This work was partially funded by Spanish Project TIN2015-71799-C2-2-P (MINECO/FEDER), by the European Union’s Horizon 2020 Research and Innovation Programme under Grant Agreement 723596 and Grant Agreement 768824, and by 2017 SGR 1537. This research article has received a grant for its linguistic revision from the Language Institute of the University of Lleida (2018 call).

Author information

Authors and Affiliations

  1. INSPIRES Research Center, University of Lleida, Lleida, Spain

    Teresa Alsinet, Josep Argelich & Ramón Béjar

  2. Starloop Studios, Lleida, Spain

    Joel Cemeli

Authors
  1. Teresa Alsinet
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Josep Argelich
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Ramón Béjar
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Joel Cemeli
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Teresa Alsinet.

Ethics declarations

Conflict of interest

Author J. Cemeli has a contract with Company Starloop Studios. Authors T. Alsinet, J. Argelich, and R. Béjar declare that they have no conflict of interest.

Ethical approval

This article does not contain any studies with human participants or animals performed by any of the authors.

Additional information

Communicated by C. Noguera.

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Alsinet, T., Argelich, J., Béjar, R. et al. A distributed argumentation algorithm for mining consistent opinions in weighted Twitter discussions. Soft Comput 23, 2147–2166 (2019). https://doi.org/10.1007/s00500-018-3380-x

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00500-018-3380-x

Keywords

Search

Navigation