EiTAKA at SemEval-2018 Task 1: An Ensemble of N-Channels ConvNet and XGboost Regressors for Emotion Analysis of Tweets

Proceedings of the 12th International Workshop on Semantic Evaluation (SemEval-2018), pages 193–199 New Orleans, Louisiana, June 5–6, 2018. ©2018 Association for Computational Linguistics EiTAKA at SemEval-2018 Task 1: An Ensemble of N-Channels ConvNet and XGboost Regressors for Emotion Analysis of Tweets Mohammed Jabreel Antonio Moreno Intelligent Technologies for Advanced Knowledge Acquisition (ITAKA), Departament d’Enginyeria Inform`atica i Matem`atiques, Universitat Rovira i Virgili, Av. Pa¨ısos Catalans, 26, 43007 Tarragona, Spain <first name>.<last name>@urv.cat Abstract This paper describes our system that has been used in Task1 Affect in Tweets. We combine two different approaches. The first one called N-Stream ConvNets, which is a deep learning approach where the second one is XGboost re- gressor based on a set of embedding and lexi- cons based features. Our system was evaluated on the testing sets of the tasks outperforming all other approaches for the Arabic version of valence intensity regression task and valence ordinal classification task. 1 Introduction Sentiment Analysis is the task of automatically identifying the valence or polarity of a piece of text. This piece of text can be a user review, a doc- ument, an SMS message, a tweet, etc. According to (Mohammad, 2016), the term sentiment analy- sis also refers to determining the attitude towards a particular target or topic. The attitude can be the polarity (positive or negative), or an emotional or effectual attitude such as joy, anger, sadness and so on. Most of the researchers in sentiment analysis have focused on developing systems to determine the polarity of a given text. This involves design- ing classifiers based on a set of examples with a manually annotated sentiment polarity. Although developing systems that automatically determine the intensity (i.e. the degree or the amount) of emotions that are communicated in a text has a wide range of applications in commerce, public health, social welfare, etc., most of the work has focused on categorical classification (whether a given piece of text communicates anger, joy, sad- ness, etc.). This can be attributed to the lack of suitable annotated data (Mohammad and Bravo- M´arquez, 2017) . In task1: Affect in Tweets, the organizers pro- vide an array of tasks where systems have to au- tomatically determine the intensity of emotions (anger, fear, joy, and sadness) and the intensity of the sentiment (aka valence) of the tweeters from their tweets. They provide annotated datasets for each task with English, Arabic, and Spanish tweets (Mohammad et al., 2018). We define the tasks below: EI-reg (an emotion intensity regression task): Given a tweet and an emotion E, determine the intensity of E that best represents the mental state of the tweeter with a real-valued score between 0 (least E) and 1 (most E). EI-oc (an emotion intensity ordinal classifica- tion task): Given a tweet and an emotion E, clas- sify the tweet into one of four ordinal classes of intensity of E that best represents the mental state of the tweeter. V-reg (a sentiment intensity regression task): Given a tweet, determine the intensity of sentiment or valence …

Content truncated to 500 words