Advertisement

Opinion Classification in Conversational Content Using N-grams

  • Kristina Machova
  • Lukáš Marhefka
Part of the Studies in Computational Intelligence book series (SCI, volume 513)

Abstract

The paper introduces the problem of opinion classification related to conversational content. It describes briefly various approaches known in this field. The focus is on a novelty method which has been designed on the basis of cyclic usage of n-grams (4-grams). This method belongs to lexicon based approaches. The contribution describes implementation of this method for the Slovak language, test results of the presented implementation and discussion of the achieved results as well.

Keywords

Opinion mining conversational content web discussions n-grams 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Choi, Y., Cardie, C.: Learning with Compositional Semantics as Structural Inference for Subsentential Sentiment Analysis. In: Proc. of the EMNLP 2008, Conference on Empirical Methods in Natural Language Processing, pp. 793–801 (2008)Google Scholar
  2. 2.
    Go, A.: Twitter Sentiment Classification using Distant Supervision. Stanford University, http://cs.stanford.edu/people/alecmgo/papers/TwitterDistantSupervision09.pdf (cit. June 4, 2013)
  3. 3.
    Levallois, C.: Umigon: sentiment analysis for tweets based on lexicons and heuristics, pp. 1–4. Erasmus University Rotterdam, The Netherlands (2013)Google Scholar
  4. 4.
    Liu, B.: Sentiment Analysis and Opinion Mining (Introduction and Survey), pp. 1–168. Morgan & Claypool Publisher (May 2012)Google Scholar
  5. 5.
    Lukáč, G., Butka, P., Mach, M.: Semantically-enhanced Extension of the Discussion Analysis Algorithm in SAKE. In: SAMI 2008, 6th International Symposium on Applied Machine Intelligence and Informatics, Herľany, Slovakia, pp. 241–246 (January 2008)Google Scholar
  6. 6.
    Mach, M., Lukáč, G.: A Dedicated Information Collection as an Interface to Newsgroup Discussions. In: IIS 2007 - 18th International Conference on Information and Intelligent Systems, Varazdin, Croatia, September 12-14, pp. 163–169 (2007) ISBN 978-953-6071-30-2Google Scholar
  7. 7.
    Smatana, M., Koncz, P., Paralič, J.: Semi-automatic Annotation Tool for Aspect-based Sentiment Analysis. FEI Technical University of Kosice, pp. 1–3 (2013)Google Scholar
  8. 8.
    Taboada, M., Brooke, J., Tofiloski, M., Voll, K., Stede, M.: Lexicon-Based Methods for Sentiment Analysis. Computational Linguistics 37(2), 267–307 (2011)CrossRefGoogle Scholar
  9. 9.
    Thelwall, M., Buckley, K., Paltoglou, G., Cai, D., Kappas, A.: Sentiment Strength Detection in Short Informal Text. Journal of the American Society for Information Science and Technology 61(12), 2544–2558 (2010)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  1. 1.Dept. of Cybernetics and Artificial IntelligenceTechnical UniversityKošiceSlovakia

Personalised recommendations