#TeamINF at SemEval-2018 Task 2: Emoji Prediction in Tweets

Proceedings of the 12th International Workshop on Semantic Evaluation (SemEval-2018), pages 415–418 New Orleans, Louisiana, June 5–6, 2018. ©2018 Association for Computational Linguistics #TeamINF at SemEval-2018 Task 2: Emoji Prediction in Tweets Alison P. Ribeiro Institute of Informatics Federal University of Goi´as Goiˆania – Goi´as – Brasil alisonrib17@gmail.com N´adia F. F. da Silva Institute of Informatics Federal University of Goi´as Goiˆania – Goi´as – Brasil nadia@inf.ufg.br Abstract In this paper, we describe a methodology to predict emoji in tweets. Our approach is based on the classic bag-of-words model in conjunc- tion with word embeddings. The used clas- sification algorithm was Logistic Regression. This architecture was used and evaluated in the context of the SemEval 2018 challenge (task 2, subtask 1). 1 Introduction Over the years, technology has significantly changed the way people communicate. It was changed especially due to social media like Twit- ter1, Facebook2, WhatsApp3, among others. Such media provide users with the ability to express their opinions/emotions not only with words, but through images, the so-called emojis. However, within the context of the sentiment analysis, little research has been dedicated to ex- plore the semantics of emoji (Barbieri et al., 2016), thus becoming an interesting challenge to investi- gate. Understanding the meaning of emojis in rela- tion to their context of use is important for inde- xing multimedia information, retrieval, or content extraction systems. In addition, emoji can com- plement the meaning of a message, that is, an emoji can determine the feeling of a text, howe- ver, such emotive figures may become fragile in the ironic/sarcastic context. In this paper, we developed a methodology to predict emoji in tweets, especially our method is based on the bag-of-words model in conjunc- tion with word embeddings (GloVe4 pre-trained) and n-grams5, applying a classification algorithm. 1https://twitter.com/ 2https://www.facebook.com 3https://www.whatsapp.com/ 4https://nlp.stanford.edu/projects/glove/ 5terms composed by n words. This configuration was employed and evaluated in the SemEval 2018 challenge (task 2, subtask 1), in which the goal is to predict the emoji of a tweet (Barbieri et al., 2018). This work is organized as follows: section 2 ex- plains some related works, section 3 describes the data set, section 4 addresses the methodology ap- plied in the task, section 5 presents the results, and finally section 6 final considerations as well as fu- ture work. 2 Related Works Emojis can express diverse types of contents in a visual way, adapting to the informal style of communication in social networks. The meaning expressed by emoticons has been explored to al- low or improve various tasks related to the sen- timent analysis, as in (Hogenboom et al., 2013, 2015). Emojis can also be used to label excerpts of texts where they occur, thus making it possible to construct sentiment lexical. In this context, in (Go et al., 2009) and (Castellucci et al., 2015) use a distant supervision over the emotionally marked textual contents to form a sentiment classifier and construct a lexicon of polarity. While Novak et al. 2015 constructed lexicons and drew a map of …

Content truncated to 500 words