Distant Supervision for Emotion Classification Task using emoji2emotion

Increasing number of research in the area of distant supervision for emotion detection task requires a reliable mapping between noisy labels and emotion classes. We propose a method for an experimental creation of such a reliable mapping based on manually annotated data and quantitative relations between labels and classes on example of emojiemotion pair in a form of emoji2emotion mapping.

[1]  Ian D. Wood,et al.  Emoji as Emotion Tags for Tweets , 2016 .

[2]  Isabelle Augenstein,et al.  emoji2vec: Learning Emoji Representations from their Description , 2016, SocialNLP@EMNLP.

[3]  Petra Kralj Novak,et al.  Sentiment of Emojis , 2015, PloS one.

[4]  Yiqun Liu,et al.  Microblog Sentiment Analysis with Emoticon Space Model , 2014, Journal of Computer Science and Technology.

[5]  Saif Mohammad,et al.  Sentiment Analysis of Short Informal Texts , 2014, J. Artif. Intell. Res..

[6]  Uzay Kaymak,et al.  Exploiting Emoticons in Polarity Classification of Text , 2015, J. Web Eng..

[7]  J. Stainer,et al.  The Emotions , 1922, Nature.

[8]  Ke Xu,et al.  MoodLens: an emoticon-based sentiment analysis system for chinese tweets , 2012, KDD.

[9]  Boi Faltings,et al.  A :) Is Worth a Thousand Words: How People Attach Sentiment to Emoticons and Words in Tweets , 2013, 2013 International Conference on Social Computing.