TeamUNCC at SemEval-2018 Task 1: Emotion Detection in English and Arabic Tweets using Deep Learning

Proceedings of the 12th International Workshop on Semantic Evaluation (SemEval-2018), pages 350–357 New Orleans, Louisiana, June 5–6, 2018. ©2018 Association for Computational Linguistics TeamUNCC at SemEval-2018 Task 1: Emotion Detection in English and Arabic Tweets using Deep Learning Malak Abdullah Samira Shaikh College of Computing and Informatics University of North Carolina at Charlotte North Carolina, U.S mabdull5, sshaikh2@uncc.edu Abstract Task 1 in the International Workshop SemEval 2018, Affect in Tweets, introduces five sub- tasks (El-reg, El-oc, V-reg, V-oc, and E-c) to detect the intensity of emotions in English, Arabic, and Spanish tweets. This paper de- scribes TeamUNCC’s system to detect emo- tions in English and Arabic tweets. Our ap- proach is novel in that we present the same architecture for all the five subtasks in both English and Arabic. The main input to the system is a combination of word2vec and doc2vec embeddings and a set of psycholin- guistic features (e.g. from AffectiveTweets Weka-package). We apply a fully connected neural network architecture and obtain perfor- mance results that show substantial improve- ments in Spearman correlation scores over the baseline models provided by Task 1 or- ganizers, (ranging from 0.03 to 0.23). Tea- mUNCC’s system ranks third in subtask El-oc and fourth in other subtasks for Arabic tweets. 1 Introduction The rise and diversity of social microblogging channels encourage people to express their feel- ings and opinions on a daily basis. Consequently, sentiment analysis and emotion detection have gained the interest of researchers in natural lan- guage processing and other fields that include po- litical science, marketing, communication, social sciences, and psychology (Mohammad and Bravo- Marquez, 2017; Agarwal et al., 2011; Chin et al., 2016). Sentiment analysis refers to classifying a subjective text as positive, neutral, or nega- tive; emotion detection recognizes types of feel- ings through the expression of texts, such as anger, joy, fear, and sadness (Agarwal et al., 2011; Ek- man, 1993). SemEval is the International Workshop on Se- mantic Evaluation that has evolved from SensE- val. The purpose of this workshop is to evalu- ate semantic analysis systems, the SemEval-2018 being the 12th workshop on semantic evaluation. Task 1 (Mohammad et al., 2018) in this workshop presents five subtasks with annotated datasets for English, Arabic, and Spanish tweets. The task for participating teams is to determine the intensity of emotions in text. Further details about Task 1 and the datasets appear in Section 3. Our system covers five subtasks for both En- glish and Arabic. The input to the system are word embedding vectors (Mikolov et al., 2013a), which are applied to fully connected neural network ar- chitecture to obtain the results. In addition, all subtasks except the last one, use document-level embeddings doc2vec (Le and Mikolov, 2014) that are concatenated with different feature vectors. The models built for detecting emotions related to Arabic tweets ranked third in subtask El-oc and fourth in the other subtasks. We use both the orig- inal Arabic tweets as well as translated tweets (to English) as input. The performance of the …

Content truncated to 500 words