Sentic Neural Networks: A Novel Cognitive Model for Affective Common Sense Reasoning

  • Thomas Mazzocco
  • Erik Cambria
  • Amir Hussain
  • Qiu-Feng Wang
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7366)

Abstract

In human cognition, the capacity to reason and make decisions is strictly dependent on our common sense knowledge about the world and our inner emotional states: we call this ability affective common sense reasoning. In previous works, graph mining and multi-dimensionality reduction techniques have been employed in attempt to emulate such a process and, hence, to semantically and affectively analyze natural language text. In this work, we exploit a novel cognitive model based on the combined use of principal component analysis and artificial neural networks to perform reasoning on a knowledge base obtained by merging a graph representation of common sense with a linguistic resource for the lexical representation of affect. Results show a noticeable improvement in emotion recognition from natural language text and pave the way for more bio-inspired approaches to the emulation of affective common sense reasoning.

Keywords

AI NLP Neural Networks Cognitive Modeling Sentic Computing 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Cambria, E., Olsher, D., Kwok, K.: Sentic activation: A two-level affective common sense reasoning framework. In: AAAI, Toronto (2012)Google Scholar
  2. 2.
    Havasi, C., Speer, R., Alonso, J.: ConceptNet 3: A flexible, multilingual semantic network for common sense knowledge. In: RANLP, Borovets (2007)Google Scholar
  3. 3.
    Strapparava, C., Valitutti, A.: WordNet-Affect: An affective extension of WordNet. In: LREC, Lisbon (2004)Google Scholar
  4. 4.
    Nagano, S., Inaba, M., Kawamura, T.: Extracting semantic relations for mining of social data. In: SDoW 2010, Shanghai (2010)Google Scholar
  5. 5.
    Wiebe, J., Wilson, T., Cardie, C.: Annotating expressions of opinions and emotions in language. Language Resources and Evaluation 39(2), 165–210 (2005)CrossRefGoogle Scholar
  6. 6.
    Elliott, C.D.: The Affective Reasoner: A Process Model of Emotions in a Multi-Agent System. PhD thesis, Northwestern University, Evanston (1992)Google Scholar
  7. 7.
    Somasundaran, S., Wiebe, J., Ruppenhofer, J.: Discourse level opinion interpretation. In: COLING, Manchester (2008)Google Scholar
  8. 8.
    Wilson, T., Wiebe, J., Hoffmann, P.: Recognizing contextual polarity in phrase-level sentiment analysis. In: HLT/EMNLP, Vancouver (2005)Google Scholar
  9. 9.
    Hu, M., Liu, B.: Mining opinion features in customer reviews. In: AAAI, San Jose (2004)Google Scholar
  10. 10.
    Goertzel, B., Silverman, K., Hartley, C., Bugaj, S., Ross, M.: The Baby Webmind project. In: AISB, Birmingham (2000)Google Scholar
  11. 11.
    Cambria, E., Hussain, A.: Sentic Computing: Techniques, Tools, and Applications. Springer, Heidelberg (2012)Google Scholar
  12. 12.
    Ekman, P., Dalgleish, T., Power, M.: Handbook of Cognition and Emotion. Wiley, Chichester (1999)Google Scholar
  13. 13.
    Kapoor, A., Burleson, W., Picard, R.: Automatic prediction of frustration. International Journal of Human-Computer Studies 65, 724–736 (2007)CrossRefGoogle Scholar
  14. 14.
    Castellano, G., Kessous, L., Caridakis, G.: Multimodal emotion recognition from expressive faces, body gestures and speech. In: Doctoral Consortium of ACII, Lisbon (2007)Google Scholar
  15. 15.
    Cambria, E., Livingstone, A., Hussain, A.: The hourglass of emotions. In: Esposito, A., Vinciarelli, A., Hoffmann, R., Muller, V. (eds.) Cognitive Behavioral Systems. LNCS, Springer, Heidelberg (2012)Google Scholar
  16. 16.
    Plutchik, R.: The nature of emotions. American Scientist 89(4), 344–350 (2001)Google Scholar
  17. 17.
    Cambria, E., Benson, T., Eckl, C., Hussain, A.: Sentic PROMs: Application of sentic computing to the development of a novel unified framework for measuring health-care quality. Expert Systems with Applications 39(12), 10533–10543 (2012)CrossRefGoogle Scholar
  18. 18.
    Cambria, E., Hussain, A., Havasi, C., Eckl, C.: AffectiveSpace: Blending common sense and affective knowledge to perform emotive reasoning. In: CAEPIA, Seville, pp. 32–41 (2009)Google Scholar
  19. 19.
    Havasi, C., Speer, R., Pustejovsky, J., Lieberman, H.: Digital intuition: Applying common sense using dimensionality reduction. IEEE Intelligent Systems 24(4), 24–35 (2009)CrossRefGoogle Scholar
  20. 20.
    Wall, M., Rechtsteiner, A., Rocha, L.: Singular value decomposition and principal component analysis. In: Berrar, D., Dubitzky, W., Granzow, M. (eds.) A Practical Approach to Microarray Data Analysis, pp. 91–109. Springer (2003)Google Scholar
  21. 21.
    Eckart, C., Young, G.: The approximation of one matrix by another of lower rank. Psychometrika 1(3), 211–218 (1936)MATHCrossRefGoogle Scholar
  22. 22.
    Cambria, E., Hussain, A., Durrani, T., Havasi, C., Eckl, C., Munro, J.: Sentic computing for patient centered application. In: IEEE ICSP, Beijing, pp. 1279–1282 (2010)Google Scholar
  23. 23.
    Qian, N.: On the momentum term in gradient descent learning algorithms. Neural Networks 12, 145–151 (1999)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Thomas Mazzocco
    • 1
  • Erik Cambria
    • 2
  • Amir Hussain
    • 1
  • Qiu-Feng Wang
    • 3
  1. 1.Dept. of Computing Science and MathematicsUniversity of StirlingStirlingUK
  2. 2.Temasek LaboratoriesNational University of SingaporeSingapore
  3. 3.National Laboratory of Pattern RecognitionChinese Academy of SciencesBeijingP.R. China

Personalised recommendations