From Emojis to Sentiment Analysis

Gaël Guibon (1, 2, 3, 4, 5) , Magalie Ochs (1, 2, 3, 4, 5) , Patrice Bellot (1, 2, 3, 4, 5)

1 LSIS - Laboratoire des Sciences de l'Information et des Systèmes
2 DIMAG - Data, Information & content MAnagement Group
3 AMU - Aix Marseille Université
4 R2I - Recherche d’information et Interactions
5 ILCB - Institute of Language, Communication and the Brain

Studies on Twitter are becoming quite common these years. Even so, the majority of them did not focused on emoticons, even less on emojis. An overview of emoticons related work has been made recently [11]. However there is still too little research work related to emojis. In this paper we draw up the work and future approaches worth considering for emoji usage in Sentiment Analysis. We aim to put necessary theoretical background before using emojis for sentiment analysis. Thus, we present an emoji usage typology along with linguistic and socio-linguistic studies on the interpretation of emojis. We also introduce approaches exploiting emojis in Sentiment Analysis. We conclude by presenting our perspectives in this domain considering the evolution of emoji usages.

Keywords: Natural language processing NLP; Emoticon; Sentiment analysis; Emoji/kaomoji

Domains: Computer Science [cs]; Computation and Language [cs.CL]

Gaël Guibon, Magalie Ochs, Patrice Bellot. From Emojis to Sentiment Analysis. WACAI 2016, Lab-STICC; ENIB; LITIS, Jun 2016, Brest, France. ⟨hal-01529708⟩