资源分类
》 资源 》论文》Positive, Negative, or Neutral: Learning an Expanded Opinion Lexicon from Emoticon-Annotated Tweets

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

2019-11-21 | |  51 |   42 |   0
Abstract 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 emoticonannotated 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.

上一篇：Embedding Semantic Relations into Word Representations

下一篇：Joint Learning of Character and Word Embeddings

用户评价
全部评价

热门资源

  • Learning to Predi...

    Much of model-based reinforcement learning invo...

  • Stratified Strate...

    In this paper we introduce Stratified Strategy ...

  • The Variational S...

    Unlike traditional images which do not offer in...

  • A Mathematical Mo...

    Direct democracy, where each voter casts one vo...

  • Rating-Boosted La...

    The performance of a recommendation system reli...