Skip to main content

Advertisement

SpringerLink
Log in

An interactive multi-agent reasoning model for sentiment analysis: a case for computational semiotics

  • Published:
Artificial Intelligence Review Aims and scope Submit manuscript

Abstract

Semiotics is a domain that studies signs. For Peircean semiotics, a sign is not a dyadic entity, composed of a word and its meaning. Instead, meaning-making is a process of signification borne out of a strictly triadic relationship; in which a representative of a sign (word(s)) stands for its object (or meaning,) but never in a vacuum, and always for an interpretant. For Peirce, it is this third, this interpretant, through which the sign displays its meaning. What is even more important is that this rational process of signification is never being carried out by a single Mind, it requires a community of reasoners. In semiotic terms this article translates the sentiment analysis problem as follows: A sentence/comment is a representamen which has a sentiment value (its object) for an evolving community of reasoning agents (interpretant.) This article presents an interactive multi-agent system in which the agents implicitly model other agents, with a semiotic based approach towards sentiment analysis. It then tests the system on an original student evaluation of teachers dataset, compares the results with deep learning and other baseline techniques, and aims to propose semiotics as a reparative alternative to the dominant dichotomies—rule-based and data-based camps within artificial intelligence.

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

Similar content being viewed by others

Notes

  1. https://ai100.stanford.edu/2016-report/section-i-what-artificial-intelligence/ai-research-trends/overall-trends-and-future-ai.

  2. Volume 2, Paragragh 228. This is the standard citation format within Peircean community.

  3. Student evaluation of teachers dataset: https://github.com/computationalsemioticslab/Sentiment-dataset.

  4. If it is the case that the total sentiment values being annotated or considered are just 3, then we will have just 3 agents.

  5. Also these cases in point: Sowa (2000), Doeben-Henisch (2009), Lorkiewicz (2016) and Chen et al. (2014).

  6. For more on Peircean conception of a community of scientific inquirers Ochs (1993) is prescribed.

  7. Student evaluation of teachers dataset is open-sourced at: https://github.com/computationalsemioticslab/Sentiment-dataset.

  8. The Keras based implementation with Theano as backend is adapted for a 5-class sentiment analysis from: https://machinelearningmastery.com/develop-n-gram-multichannel-convolutional-neural-network-sentiment-analysis/.

  9. https://gist.github.com/rtkgupta/da5a7c5b66383d8db2b1.

References

  • Albrecht S, Stone P (2018) Autonomous agents modelling other agents: a comprehensive survey and open problems. Artif Intell 258:66–95. https://doi.org/10.1016/j.artint.2018.01.002

    Article  MathSciNet  MATH  Google Scholar 

  • Bhatia P, Ji Y, Eisenstein J (2015) Better document-level sentiment analysis from RST discourse parsing. In: Proceedings of the 2015 conference on empirical methods in natural language processing. Association for Computational Linguistics, Lisbon, pp 2212–2218. https://doi.org/10.18653/v1/D15-1263, https://www.aclweb.org/anthology/D15-1263

  • Bratman ME, Israel DJ, Pollack ME (1988) Plans and resource-bounded practical reasoning. Comput Intell 4(4):349–355

    Article  Google Scholar 

  • Brooks RA (1991) Intelligence without reason. In: Proceedings of the 12th international joint conference on artificial intelligence. IJCAI’91, vol 1. Morgan Kaufmann Publishers Inc., San Francisco, pp 569–595. http://dl.acm.org/citation.cfm?id=1631171.1631258

  • Camara M, Bonham-Carter O, Jumadinova J (2015) A multi-agent system with reinforcement learning agents for biomedical text mining. In: Proceedings of the 6th ACM conference on bioinformatics, computational biology and health informatics, BCB ’15. ACM, New York, pp 634–643. https://doi.org/10.1145/2808719.2812596

  • Cambria E (2016) Affective computing and sentiment analysis. IEEE Intell Syst 31(2):102–107. https://doi.org/10.1109/MIS.2016.31

    Article  Google Scholar 

  • Chang AX, Savva M, Manning CD (2014) Semantic parsing for text to 3d scene generation. In: ACL 2014, vol 17

  • Chen X, Gao H, Liu K, Zhang Y (2014) Incorporating semiotics into fuzzy logic to enhance clinical decision support systems. Springer, Berlin, pp 97–106. https://doi.org/10.1007/978-3-642-55355-4_10

  • Doeben-Henisch G (2009) Humanlike computational learning theory. A computational semiotics perspective. In: AFRICON, 2009. AFRICON’09. IEEE, pp 1–6

  • Gudwin R, Queiroz J (2005) Towards an introduction to computational semiotics. In: International conference on integration of knowledge intensive multi-agent systems, 2005. IEEE, pp 393–398

  • Guerini M, Gatti L, Turchi M (2013) Sentiment analysis: how to derive prior polarities from SentiWordNet. In: Proceedings of the 2013 conference on empirical methods in natural language processing. Association for Computational Linguistics, Seattle, pp 1259–1269. https://www.aclweb.org/anthology/D13-1125

  • Israel D (2013) Random thoughts on random natural language processing research. Leonardo Art/Science Evening Rendezvous, SRI International

    Google Scholar 

  • Jansen P, Surdeanu M, Clark P (2014) Discourse complements lexical semantics for non-factoid answer reranking. In: ACL, vol 1, pp 977–986

  • Joslyn C, Rocha LM (2000) Towards semiotic agent-based models of socio-technical organizations. In: Sarjoughian HS et al (ed) Proceedings of the AI and simulation 2000, pp 70–79

  • Jovanoski D, Pachovski V, Nakov P (2015) Sentiment analysis in twitter for macedonian. In: RANLP, Citeseer, pp 249–257

  • Kim Y (2014) Convolutional neural networks for sentence classification. In: Proceedings of the 2014 conference on empirical methods in natural language processing (EMNLP). Association for Computational Linguistics, Doha, pp 1746–1751. https://doi.org/10.3115/v1/D14-1181, https://www.aclweb.org/anthology/D14-1181

  • Kraus S, Sycara K, Evenchik A (1998) Reaching agreements through argumentation: a logical model and implementation. Artif Intell 104(1):1–69. https://doi.org/10.1016/S0004-3702(98)00078-2

    Article  MathSciNet  MATH  Google Scholar 

  • Le Q, Mikolov T (2014) Distributed representations of sentences and documents. In: Proceedings of the 31st international conference on international conference on machine learning. ICML’14, vol 32. JMLR.org, pp II-1188–II-1196. http://dl.acm.org/citation.cfm?id=3044805.3045025

  • Li Y, Pan Q, Yang T, Wang S, Tang J, Cambria E (2017) Learning word representations for sentiment analysis. Cogn Comput 9(6):843–851. https://doi.org/10.1007/s12559-017-9492-2

    Article  Google Scholar 

  • Lipenkova J (2015) A system for fine-grained aspect-based sentiment analysis of Chinese. In: ACL (system demonstrations), pp 55–60

  • Lorkiewicz W (2016) Issues on two-layer object perception in the process of artificial semiosis. In: 2016 third European network intelligence conference (ENIC), pp 165–172. https://doi.org/10.1109/ENIC.2016.032

  • Ma Y, Peng H, Cambria E (2018) Targeted aspect-based sentiment analysis via embedding commonsense knowledge into an attentive LSTM. In: Proceedings of the thirty-second AAAI conference on artificial intelligence, USA, February 2–7, pp 5876–5883. https://www.aaai.org/ocs/index.php/AAAI/AAAI18/paper/view/16541

  • Manning CD (2015) Computational linguistics and deep learning. Comput Linguist 41(4):701–707. https://doi.org/10.1162/COLI_a_00239

    Article  MathSciNet  Google Scholar 

  • Marcus GF (2004) Before the word. Nature 431:745

    Article  Google Scholar 

  • Mihalcea R, Corley C, Strapparava C (2006) Corpus-based and knowledge-based measures of text semantic similarity. In: Proceedings of the 21st national conference on artificial intelligence. AAAI’06, vol 1, pp 775–780. AAAI Press, Palo Alto. http://dl.acm.org/citation.cfm?id=1597538.1597662

  • Narayan S, Gardent C (2014) Hybrid simplification using deep semantics and machine translation. In: The 52nd annual meeting of the association for computational linguistics, pp 435–445

  • Nguyen TH, Shirai K (2015) Topic modeling based sentiment analysis on social media for stock market prediction. In: ACL, vol 1, pp 1354–1364

  • Nöth W (1995) Handbook of semiotics. Advances in semiotics. Indiana University Press, pp 41–42. https://books.google.com.pk/books?id=rHA4KQcPeNgC

  • Ochs PW (1993) Founders of constructive postmodern philosophy. State University of New York Press, Albany, pp 68, 85

  • Peirce C, Houser N, Kloesel C, Project PE (1998) What is a sign? Chap. 2. In: Houser N, Kloesel CJW (eds) The essential peirce: selected philosophical writings, vol 2. Indiana University Press, Bloomington. https://books.google.com.pk/books?id=grYAoECfZtIC

  • Peirce CS (1931–1958) The collected papers of Charles Sanders Peirce, vols I–VIII. Harvard University Press, Cambridge

  • Pospelov D (1991) Translation of book situational control: theory and practice. https://books.google.com.pk/books?id=BOpBAQAACAAJ

  • Rao AS, Georgeff MP (1995) BDI agents: from theory to practice. In: Proceedings of the first international conference on multi-agent systems, ICMAS-95, pp 312–319

  • Reiter E (2007) The shrinking horizons of computational linguistics. Comput Linguist 33(2):283–287

    Article  Google Scholar 

  • Saad F (2014) Baseline evaluation: an empirical study of the performance of machine learning algorithms in short snippet sentiment analysis. In: Proceedings of the 14th international conference on knowledge technologies and data-driven business, i-KNOW ’14. ACM, New York, pp 6:1–6:8. https://doi.org/10.1145/2637748.2638420

  • Saussure FD, Baskin W (1969) Course in general linguistics. McGraw-Hill Book, New York

    Google Scholar 

  • Seuren P (1998) Western linguistics: an historical introduction. Wiley, Oxford. https://books.google.com.pk/books?id=YD7fupu-qS0C

  • Short TL (1996) Interpreting peirce’s interpretant: a response to Lalor, Liszka, and Meyers. Trans Charles S. Peirce Soc 32(4):488–541

    Google Scholar 

  • Socher R, Perelygin A, Wu JY, Chuang J, Manning CD, Ng AY, Potts C (2013) Recursive deep models for semantic compositionality over a sentiment treebank. In: EMNLP

  • Sowa JF (2000) Ontology, metadata, and semiotics. In: Conceptual structures: logical, linguistic, and computational issues: 8th international conference on conceptual structures. ICCS 2000, Darmstadt, Germany, August 14–18, 2000. Proceedings, pp 55–81. Springer, Berlin. https://doi.org/10.1007/10722280_5

  • Stone P, Brooks R, Brynjolfsson E, Calo R, Etzioni O, Hager G, Hirschberg J, Kalyanakrishnan S, Kamar E, Kraus S, Leyton-Brown K, Parkes D, Press W, Saxenian A, Shah J, Tambe M, Teller A (2016) Artificial intelligence and life in 2030—one hundred year study on artificial intelligence. In: Report of the 2015–2016 study panel. Stanford University, Stanford

  • Yin Y, Song Y, Zhang M (2017) Document-level multi-aspect sentiment classification as machine comprehension. In: EMNLP

  • Young T, Cambria E, Chaturvedi I, Zhou H, Biswas S, Huang M (2018) Augmenting end-to-end dialogue systems with commonsense knowledge. In: Proceedings of the thirty-second AAAI conference on artificial intelligence, USA, February 2–7, 2018, pp 4970–4977. https://www.aaai.org/ocs/index.php/AAAI/AAAI18/paper/view/16573

  • Yu M, Dredze M (2014) Improving lexical embeddings with semantic knowledge. In: ACL, vol 2, pp 545–550

  • Zhao W, Peng H, Eger S, Cambria E, Yang M (2019) Towards scalable and reliable capsule networks for challenging NLP applications. In: Proceedings of the 57th conference of the association for computational linguistics, ACL 2019, Florence, Italy, July 28–August 2, 2019, vol 1. Long Papers, pp 1549–1559. https://www.aclweb.org/anthology/P19-1150/

Download references

Acknowledgements

I would like to acknowledge Professor Peter Ochs for the detailed discussions which germinated this idea; my colleague, Ambreen Hanif for helping with compilation of the dataset and some of the comparative results; my research assistants, Sana Bokhari and Muhammad Ali for conducting early stage surveys.

Author information

Authors and Affiliations

  1. Namal Institute, Mianwali, Pakistan

    Junaid Akhtar

Authors
  1. Junaid Akhtar
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Junaid Akhtar.

Additional information

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

Akhtar, J. An interactive multi-agent reasoning model for sentiment analysis: a case for computational semiotics. Artif Intell Rev 53, 3987–4004 (2020). https://doi.org/10.1007/s10462-019-09785-6

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10462-019-09785-6

Keywords

Search

Navigation