Locked History Actions


This is the home page of the Polish sentiment dictionary (Slownik Wydzwieku).

The list can be downloaded here.

Word sentiment was computed using several classifiers and formulas described in:

  1. A. Wawer. Mining Co-Occurrence Matrices for SO-PMI Paradigm Word Candidates. In Proceedings of the Student Research Workshop at the 13th Conference of the European Chapter of the Association for Computational Linguistics, EACL’12 SRW, pages 74–80, Avignon, France, April 2012a. Association for Computational Linguistics. 3, 44.

  2. A. Wawer and D. Rogozinska. How Much Supervision? Corpus-based Lexeme Sentiment Estimation. In Data Mining Workshops, 2012 IEEE 12th International Conference on. SENTIRE 2012., ICDMW, pages 724–730, Los Alamitos, CA, USA, Dec. 2012. IEEE Computer Society.

  3. A.Wawer. Extracting Emotive Patterns for Languages with Rich Morphology. International Journal of Computational Linguistics and Applications, 3(1), Jan-Jun 2012b.

The first three columns reflect sentiment scores computed using supervised methods as in [2]:

  • Neutral (0) vs positive or negative (1).
  • Negative (-1), neutral (0), positive (1).
  • Very negative (-2), negative (-1), neutral (0), positive (1), very positive (2).

The last column is the SO-PMI score calculated using the svd-based paradigm words selection described in [1].