Mutux at SemEval-2018 Task 1: Exploring Impacts of Context Information On Emotion Detection

Proceedings of the 12th International Workshop on Semantic Evaluation (SemEval-2018), pages 345–349 New Orleans, Louisiana, June 5–6, 2018. ©2018 Association for Computational Linguistics Mutux at SemEval-2018 Task 1: Exploring Impacts of Context Information On Emotion Detection Pan Du DIRO, University of Montreal pandu@iro.umontreal.ca Jian-Yun Nie DIRO, University of Montreal nie@iro.umontreal.ca Abstract This paper describes MuTuX, our system that is designed for task 1-5a, emotion classifica- tion analysis of tweets on SemEval20181. The system aims at exploring the potential of con- text information of terms for emotion analy- sis. A Recurrent Neural Network is adopted to capture the context information of terms in tweets. Only term features and the sequential relations are used in our system. The result submitted ranks 16th out of 35 systems on the task of emotion detection in English-language tweets. 1 Introduction Emotion analysis on social media is attracting more and more reserach interests (Strapparava and Mihalcea, 2008; Balahur et al., 2011; Agrawal and An, 2012; Wang et al., 2012; Hasan et al., 2014a; Canales and Mart´ınez-Barco, 2014) from indus- try and academia. Commercial applications such as product recommendation, online retailing, and marketing are turning their interests from tradi- tional sentiment analysis to emotion analysis as well. Emotion analysis is generally taken as a multi-lable classification problem. Given a piece of text, such as a tweet, it assigns several lables such as depressed, sad, angry and so on to it (Mo- hammad et al., 2018) based on the meaning con- tained in the text. Techniques related to emotion detection can be divided into lexicon-based approaches (Valitutti, 2004; Strapparava and Mihalcea, 2008; Balahur et al., 2011) and machine learning approaches (Hasan et al., 2014b; Wang et al., 2012; Roberts et al., 2012; Suttles and Ide, 2013). Lexicon- based approaches leverage lexical resources to detect emotions, the resources can be keywords (Hasan et al., 2014a), WordNet-Affect (Valitutti, 1https://competitions.codalab.org/competitions/17751 2004), ontologies (Balahur et al., 2011) and so on. Machine learning based approaches (Bala- bantaray et al., 2012) generally take emotion de- tection as a classification problem using SVM, neural network (Abdul-Mageed and Ungar, 2017; Bravo-Marquez et al., 2016), naieve bayes, Deci- sion Tree, KNN and so on, or using certain un- supervised techniques such as LSA (Deerwester et al., 1990; Wang and Zheng, 2013; Gill et al., 2008), pLSA, NMF to transform the feature space into a more reasonable one before conducting clas- sification. The main challenges of emotion analy- sis of tweets are the following: 1. Informal languages used on social media are not always obeying formal grammar, which makes traditional grammatical features less reliable for detecting emotions on social me- dia. 2. New words are frequently created on social media, making it difficult to understand their emotional meaning even for a human being. To address the challenges above, we use re- current neural network to make use of terms, se- quential information, and contextual information simultaneously for emotion detection. We believe that contextual information can partly solve the new-term problem and grammar-breach problem. To use recurrent neural network, …

Content truncated to 500 words