Unsupervised Improving of Sentiment Analysis Using Global Target Context

Authors: Ivan Habernal, Tomáš Brychcín {habernal | brychcin} at kiv.zcu.cz

The article is available at nlp.kiv.zcu.cz under "Publications" section.

Corpora

CSFD CZ — 90k reviews with their related target (movie): csfd-90k-reviews-ranlp2013.tar.bz2 (11 MB)

Licence

The corpus is licenced under Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License

Citation

Please, cite our article if you use any of the available resources.

@InProceedings{Habernal.Brychcin.2013b,
  author    = {Ivan Habernal and Tom\'a\v{s} Brychc\'{i}n},
  title     = {Unsupervised Improving of Sentiment Analysis Using Global Target Context},
  booktitle = {Proceedings of RANLP 2013},
  year      = {2013},
  publisher = {Association for Computational Linguistics},
  pages     = {TBD},
  url       = {TBD}
}

Sentiment Analysis in Czech Social Media Using Supervised Machine Learning

Authors: Ivan Habernal, Tomáš Ptáček and Josef Steinberger (habernal | tigi | jstein @ kiv.zcu.cz)

Our article provides an in-depth research of machine learning methods for sentiment analysis of Czech social media. We also created a large human-annotated Czech social media corpus.
More details can be found in our article.

Article Resources

Corpora

CSFD CZ Corpus contains 91,381 movie reviews (30,897 positive, 30,768 neutral, and 29,716 negative reviews) from the Czech Movie Database Corpus: csfd.zip (~13 MB)

Facebook CZ Corpus consists 10,000 Facebook posts (2,587 positive, 5,174 neutral, 1,991 negative and 248 bipolar posts).
Corpus: facebook.zip (~1.5 MB) The archive contains data and statistics in an Excel file (FBData.xlsx) and gold data in two text files with posts (gold-posts.txt) and labels (gols-labels.txt) on corresponding lines.

Mall CZ Corpus consists 145,307 user product reviews (102,977 positive, 31,943 neutral, and 10,387 negative) crawled from a large Czech e-shop Mall.cz
Corpus: mallcz.zip (~7.4 MB)

Software

Licensing rights for the project are not yet resolved, therefore the software is available only on request by mail.

Licence

Corpus is licenced under Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License

Citation

Please, cite our article if you use any of the available resources.

@InProceedings{Habernal.et.al.2013,
  author    = {Ivan Habernal and Tom\'a\v{s} Pt\'a\v{c}ek and Josef Steinberger},
  title     = {Sentiment Analysis in Czech Social Media Using Supervised Machine Learning},
  booktitle = {Proceedings of the 4th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis},
  month     = {June},
  year      = {2013},
  address   = {Atlanta, Georgia},
  publisher = {Association for Computational Linguistics},
  pages     = {65--74},
  url       = {http://www.aclweb.org/anthology/W13-1609}
}

Last change: 2013-07-17