Advertisement

Assessing Sentiment of Text by Semantic Dependency and Contextual Valence Analysis

  • Mostafa Al Masum Shaikh
  • Helmut Prendinger
  • Ishizuka Mitsuru
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4738)

Abstract

Text is not only an important medium to describe facts and events, but also to effectively communicate information about the writer’s (positive or negative) sentiment underlying an opinion, and an affect or emotion (e.g. happy, fearful, surprised etc.). We consider sentiment assessment and emotion sensing from text as two different problems, whereby sentiment assessment is a prior task to emotion sensing. This paper presents an approach to sentiment assessment, i.e. the recognition of negative or positive sense of a sentence. We perform semantic dependency analysis on the semantic verb frames of each sentence, and apply a set of rules to each dependency relation to calculate the contextual valence of the whole sentence. By employing a domain-independent, rule-based approach, our system is able to automatically identify sentence-level sentiment. Empirical results indicate that our system outperforms another state-of-the-art approach.

Keywords

Sentiment Analysis Word Sense Disambiguation Affective Verb Name Entity Input Sentence 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Esuli, A., Sebastiani, F.: Determining the semantic orientation of terms through gloss analysis. In: Proc. CIKM, pp. 617–624 (2005)Google Scholar
  2. 2.
    Fellbaum, C. (ed.): WordNet: An Electronic Lexical Databases. MIT Press, Cambridge, Massachusetts (1999)Google Scholar
  3. 3.
    Fitrianie, S., Rothkrantz, L.J.M.: Constructing Knowledge for Automated Text-Based Emotion Expressions. In: Proc. CompSysTech (2006)Google Scholar
  4. 4.
    Fleiss, J.L.: Measuring nominal scale agreement among many raters. Psychological Bulletin 76(5), 378–382 (1971)CrossRefGoogle Scholar
  5. 5.
    Hu, M., Liu, B.: Mining and summarizing customer reviews. In: Proc. KDD (2004)Google Scholar
  6. 6.
    Kamps, J., Marx, M.: Words with Attitude. In: Proc. 1st Intl. WordNet Conf. (2002)Google Scholar
  7. 7.
    Kim, S.M., Hovy, E.H.: Identifying and Analyzing Judgment Opinions. In: Proc. HLT-NAACL 2006, ACL, pp. 200–207 (2006)Google Scholar
  8. 8.
    Kim, S.M., Hovy, E.H.: Automatic Detection of Opinion Bearing Words and Sentences. In: Companion Volume to the Proceedings of the 2nd IJCNLP (2005)Google Scholar
  9. 9.
    Liu, H., Lieberman, H., Selker, T.: A Model of Textual Affect Sensing using Real-World Knowledge. In: Proc. IUI, Miami, FL, January 12-15, pp. 125–132. ACM, New York (2003)Google Scholar
  10. 10.
    Liu, H., Singh, P.: ConceptNet: A Practical Commonsense Reasoning Toolkit. BT Technology Journal 22(4), 211–226 (2004)CrossRefGoogle Scholar
  11. 11.
    Machinese Syntax, the official website (2005), http://www.connexor.com/connexor/
  12. 12.
    Mihalcea, R., Liu, H.: A corpus-based approach to finding happiness, Computational approaches for analysis of weblogs. In: AAAI Spring Symposium (2006)Google Scholar
  13. 13.
    Nasukawa, T., Yi, J.: Sentiment Analysis: Capturing Favorability Using Natural Language Processing. In: Proc. K-CAP, pp. 70–77. ACM Press, New York (2003)CrossRefGoogle Scholar
  14. 14.
    Pang, B., Lee, L.: Seeing stars: Exploiting class relationships for sentiment categorization with respect to rating scales. In: Proc. ACL, pp. 115–124 (2005)Google Scholar
  15. 15.
    Pennebaker, J.W., Mehl, M.R., Niederhoffer, K.: Psychological aspects of natural language use: Our words, our selves. Annual Review of Psychology 54, 547–577 (2003)CrossRefGoogle Scholar
  16. 16.
    Polanyi, L., Zaenen, A.: Contextual valence shifters. In: Shanahan, J., Qu, Y., Wiebe, J. (eds.) Computing Attitude and Affect in Text: Theory and Applications, The Information Retrieval Series, vol. 20, pp. 1–10 (2004)Google Scholar
  17. 17.
    Riloff, E., Wiebe, J., Wilson, T.: Learning Subjective Nouns Using Extraction Pattern Bootstrapping. In: Proc. CoNLL 2003 (2003)Google Scholar
  18. 18.
    Shaikh, M.A.M., Prendinger, H., Ishizuka, M.: SenseNet: A Linguistic Tool to Visualize Numerical-Valance Based Sentiment of Textual Data. In: Proc. ICON, pp. 147–152 (2007)Google Scholar
  19. 19.
    Subasic, P., Huettner, A.: Affect Analysis of Text Using Fuzzy Semantic Typing. IEEE Transactions on Fuzzy Systems 9(4), 483–496 (2001)CrossRefGoogle Scholar
  20. 20.
    Stock, O., Strapparava, C.: Getting Serious about the Development of Computational Humor. In: Proc. IJCAI, pp. 59–64 (2003)Google Scholar
  21. 21.
    Turney, P.: Thumbs Up or Thumbs Down? Semantic Orientation Applied to Unsupervised Classification of Reviews. In: Proc. 40th Annual Meeting of the ACL, pp. 417–424 (2002)Google Scholar
  22. 22.
    Valitutti, A., Strapparava, C., Stock, O.: Developing Affective Lexical Resources. PsychNology Journal 2(1), 61–83 (2004)Google Scholar
  23. 23.
    Wiebe, J., Mihalcea, R.: Word Sense and Subjectivity. In: Proc. ACL 2006, pp. 1065–1072 (2006)Google Scholar
  24. 24.
    Wiebe, J.: Learning subjective adjectives from corpora. In: Proc. AAAI (2000)Google Scholar
  25. 25.
    Wiebe, J., Wilson, T., Cardie, C.: Annotating expressions of opinions and emotions in language. Language Resources and Evaluation 39(2-3), 165–210 (2005)CrossRefGoogle Scholar
  26. 26.
    Wilson, T., Wiebe, J., Hoffmann, P.: Recognizing Contextual Polarity in Phrase-Level Sentiment Analysis. In: Proc. HLT/EMNLP. ACL, pp. 347–354 (2005)Google Scholar
  27. 27.

Copyright information

© Springer-Verlag Berlin Heidelberg 2007

Authors and Affiliations

  • Mostafa Al Masum Shaikh
    • 1
  • Helmut Prendinger
    • 2
  • Ishizuka Mitsuru
    • 1
  1. 1.Department of Information and Communication Engineering, University of Tokyo, 7-3-1 Hongo, Bunkyo-ku, 113-8656 TokyoJapan
  2. 2.Digital Contents and Media Sciences Research Division, National Institute of Informatics, 2-1-2 Hitotsubashi, Chiyoda-ku, 101-8430 TokyoJapan

Personalised recommendations