Bravo-Márquez, F., Frank, E., & Pfahringer, B. (2015). Positive, Negative, or Neutral: Learning an Expanded Opinion Lexicon from Emoticon-annotated Tweets. In Q. Yang & M. Wooldridge (Eds.), Proc 24th International Joint Conference on Artificial Intelligence (pp. 1229–1235). Buenos Aires, Argentina: AAAI Press.
Permanent Research Commons link: http://hdl.handle.net/10289/9630
We present a supervised framework for expanding an opinion lexicon for tweets. The lexicon contains part-of-speech (POS) disambiguated entries with a three-dimensional probability distribution for positive, negative, and neutral polarities. To obtain this distribution using machine learning, we propose word-level attributes based on POS tags and information calculated from streams of emoticon annotated tweets. Our experimental results show that our method outperforms the three-dimensional word-level polarity classification performance obtained by semantic orientation, a state-of-the-art measure for establishing world-level sentiment.
This is an author's accepted version of a paper published in the Proceedings of the 24th International Joint Conference on Artificial Intelligence. © 2015 International Joint Conferences on Artificial Intelligence.