Positive, Negative, or Neutral: Learning an Expanded Opinion Lexicon from Emoticon-annotated Tweets

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 pos-itive, negative, and neutral polarities. To obtain this distribution using machine learning, we pro-pose 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 ob-tained by semantic orientation, a state-of-the-art measure for establishing world-level sentiment.