Evaluation of the Delta TF-IDF Features for Sentiment Analysis

  • Andrew B. SamoylovEmail author
Conference paper
Part of the Communications in Computer and Information Science book series (CCIS, volume 436)


This paper proposes a feature model different from bag-of-word models to analyze the sentiment of the text. The main idea of the method is improving the quality of prediction by combining a rule-based approach and the standard bag-of-words model. Results of the experiments with changing the subject, the size of reviews in data are shown. The hypothesis stating that it is better to use short message with the length of 1–2 sentences or tweets for calculation Delta TFIDF was tested.


Sentiment analysis Tweets Subjective an objective sentences Delta TFIDF 


  1. 1.
    Liu, B.: Sentiment Analysis and Subjectivity - Handbook of Natural Language Processing, 2nd edn. Taylor and Francis Group, Boca (2010)Google Scholar
  2. 2.
    Pang, B., Lee, L., Vaithyanathan, S.: Thumbs up? Sentiment classification using machine learning techniques. In: Proceedings of EMNLP, pp. 79–86 (2002)Google Scholar
  3. 3.
    Pang, B., Lee, L.: A sentimental education: Sentiment analysis using subjectivity summarization based on minimum cuts. In: Proceedings of the ACL (2004)Google Scholar
  4. 4.
    Martineau, J., Finin, T.: Delta TFIDF: An improved feature space for sentiment analysis. In: Third AAAI Internatonal Conference on Weblogs and Social Media, May 2009, San Jose, CA (Preprint) (2009)Google Scholar
  5. 5.
    Paltoglou, G., Thelwall, M.: A study of information retrieval weighting schemes for sentiment analysis. In: Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics, pp. 1386–1395. Uppsala, Sweden (2010)Google Scholar
  6. 6.
    Pang, B., Lillian, L.: A sentimental education: sentiment analysis using subjectivity summarization based on minimum cuts. In: Proceeding ACL ’04 Proceedings of the 42nd Annual Meeting on Association for Computational Linguistics Article No. 271, USA (2004)Google Scholar
  7. 7.
    Taboada, M., Brooke, J., Tofiloski, M., Voll, K., Stede, M.: Lexicon-based methods for sentiment analysis. J. Comput. Linguist. 37(2), 267–307 (2011)CrossRefGoogle Scholar
  8. 8.
    Peter, D.T.: Thumbs up or thumbs down? Semantic orientation applied to unsupervised classification of reviews. In: Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics (ACL), Philadelphia, pp. 417–424, July 2002Google Scholar
  9. 9.
    Breiman, L.: Random forests. Mach. Learn. 45(1), 5–32 (2001)CrossRefzbMATHGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  1. 1.Southern Federal UniversityRostov-on-DonRussia

Personalised recommendations