UWB at SemEval-2018 Task 1: Emotion Intensity Detection in Tweets

Proceedings of the 12th International Workshop on Semantic Evaluation (SemEval-2018), pages 133–140 New Orleans, Louisiana, June 5–6, 2018. ©2018 Association for Computational Linguistics UWB at SemEval-2018 Task 1: Emotion Intensity Detection in Tweets Pavel Pˇrib´aˇn1,2, Tom´aˇs Hercig1,2, and Ladislav Lenc1 1NTIS – New Technologies for the Information Society, Faculty of Applied Sciences, University of West Bohemia, Czech Republic 2Department of Computer Science and Engineering, Faculty of Applied Sciences, University of West Bohemia, Czech Republic {pribanp,tigi,llenc}@kiv.zcu.cz http://nlp.kiv.zcu.cz Abstract This paper describes our system created for the SemEval-2018 Task 1: Affect in Tweets (AIT- 2018). We participated in both the regression and the ordinal classification subtasks for emo- tion intensity detection in English, Arabic, and Spanish. For the regression subtask we use the Affecti- veTweets system with added features using va- rious word embeddings, lexicons, and LDA. For the ordinal classification we additionally use our Brainy system with features using parse tree, POS tags, and morphological fea- tures. The most beneficial features apart from word and character n-grams include word em- beddings, POS count and morphological fea- tures. 1 Introduction The task of Detecting Emotion Intensity assigns the intensity to a tweet with given emotion. The emotions include anger, fear, joy, and sadness. The intensity is either on a scale of zero to one for the regression subtask, or one of four classes (0:no, 1: low, 2: moderate, 3: high) for the classification subtask. The task was prepared in three languages: English, Arabic, and Spanish. For each language there are four training and test sets of data – one for each emotion. The data creation is described in (Mohammad and Kiritchenko, 2018) and detai- led description of the task is in (Mohammad et al., 2018). We participated in the emotion intensity regres- sion task (EI-reg) and in the emotion intensity or- dinal classification task (EI-oc) in English, Arabic and Spanish. 2 System Description We used two separate systems for ordinal classi- fication – AffectiveTweets (Section 3) and Brainy (Section 4). For the regression task we just use the AffectiveTweets system. We train a separate mo- del for each emotion. The Brainy system perfor- med better in our pre-evaluation experiments on the development data for all emotions in Spanish and for fear and joy emotions in Arabic. 3 AffectiveTweets System 3.1 Tweets Preprocessing Tweets often contain slang expressions, misspelled words, emoticons or abbreviati- ons and it’s needed to make some preprocessing steps before extracting features. First, every tweet was tokenized using TweetNLP1(Gimpel et al., 2011). Then the AffectiveTweets2 (Mohammad and Bravo-Marquez, 2017) package for Weka machine learning workbench (Hall et al., 2009) was used for feature extraction. The following steps were applied on tokens for every language in both tasks: 1. Tokens were converted to lowercase 2. URL links were replaced with http://www.url.com token 3. Twitter usernames (tokens starting with @) were replaced with @user token 4. Tokens containing sequences of letters occurring more than two times in a row were replaced with two occurrences of them (e.g. huuuungry is reduced to huungry, …

Content truncated to 500 words