PickleTeam! at SemEval-2018 Task 2: English and Spanish Emoji Prediction from Tweets

Proceedings of the 12th International Workshop on Semantic Evaluation (SemEval-2018), pages 454–458 New Orleans, Louisiana, June 5–6, 2018. ©2018 Association for Computational Linguistics PickleTeam! at SemEval-2018 Task 2: English and Spanish Emoji Prediction from Tweets Daphne Groot University of Groningen d.groot.2@student.rug.nl R´emon Kruizinga University of Groningen r.kruizinga.2@student.rug.nl Hennie Veldthuis University of Groningen h.veldthuis@student.rug.nl Simon de Wit University of Groningen s.de.wit.2@student.rug.nl Hessel Haagsma University of Groningen hessel.haagsma@rug.nl Abstract We present a system for emoji prediction on English and Spanish tweets, prepared for the SemEval-2018 task on Multilingual Emoji Prediction. We compared the performance of an SVM, LSTM and an ensemble of these two. We found the SVM performed best on our development set with an accuracy of 61.3% for English and 83% for Spanish. The fea- tures used for the SVM are lowercased word n-grams in the range of 1 to 20, tokenised by a TweetTokenizer and stripped of stop words. On the test set, our model achieved an accu- racy of 34% on English, with a slightly lower score of 29.7% accuracy on Spanish. 1 Introduction The way people communicate with each other has changed since the rise of social media. Many peo- ple use visual icons, so-called emojis, to com- plement their social media messages. Emojis are frequently used on online platforms like Twitter, Facebook, Instagram and WhatsApp. The wide use of emojis in social media means that process- ing these emojis can be relevant for NLP applica- tions dealing with social media data. Social media text has been studied in the field of author profiling, but only recently the interest in the research on emojis started growing. Author profiling is used in different fields such as market- ing, forensics, psychological research and medical diagnosis. Author profiling focuses on stylomet- ric features, and since this new popular way of expressing meaning by using emojis has become mainstream, its important to research if and how this data can be used in addition to the textual data. It could be possible that emojis reveal a great deal about the author’s gender, location, age or other characteristics. We describe our approach to SemEval-2018 Task 2 on Multilingual Emoji Prediction (Barbi- eri et al., 2018) in this paper. We will discuss the features, the machine learning methods we used and analyse the performance of our best method. 2 Related Work Author profiling tasks are focusing more and more on social media. Oftentimes, the data that is pro- vided is data obtained from social media platforms Rangel et al. (2017). However, research on emojis is more scarce. Some research on emojis is done by Barbieri et al. (2017). They investigated the re- lation between words and emojis, and found that neural models outperform baseline bag-of-words models as well as humans when predicting which emojis are used in tweets. Xie et al. (2016) researched automatic emoji recommendation using neural networks. Emo- jis can express more delicate feelings beyond plain text, and suggesting valid emojis to users of messaging systems can enhance user experi- ence. They …

Content truncated to 500 words