INGEOTEC at SemEval-2018 Task 1: EvoMSA and μTC for Sentiment Analysis

Proceedings of the 12th International Workshop on Semantic Evaluation (SemEval-2018), pages 146–150 New Orleans, Louisiana, June 5–6, 2018. ©2018 Association for Computational Linguistics INGEOTEC at SemEval-2018 Task 1: EvoMSA and µTC for Sentiment Analysis Mario Graff and Sabino Miranda-Jim´enez∗and Eric S. Tellez CONACyT - INFOTEC, Aguascalientes, M´exico {mario.graff,sabino.miranda,eric.tellez}@infotec.mx Daniela Moctezuma CONACyT - CentroGEO, Aguascalientes, M´exico dmoctezuma@centrogeo.edu.mx Abstract This paper describes our participation in Affective Tweets task for emotional intensity and sentiment intensity subtasks for English, Spanish, and Ara- bic languages. We used two approaches, µTC and EvoMSA. The first one is a generic text catego- rization and regression system; and the second one is a two-stage architecture for Sentiment Analysis. Both approaches are multilingual and domain in- dependent. 1 Introduction Sentiment Analysis is a research area where does a computational analysis of people’s feelings or be- liefs expressed in texts such as emotions, opinions, attitudes, appraisals, etc. (Liu and Zhang, 2012). People communicate not only the emotion or sen- timent they are feeling, but also the intensity, that is, the degree of emotion or sentiment. In this con- text, SemEval is one of the forums that conducts evaluations on semantics at different levels, for in- stance, it proposes tasks such as sentiment analy- sis, the intensity of emotion or sentiment (affective tweets) (Mohammad et al., 2018), irony detection, among others (SemEval, 2017). In this work, we present the results of our par- ticipation in Affective Tweets task for four of the five subtasks in English, Spanish, and Arabic lan- guages and for all emotions available: anger, fear, joy, and sadness. The subtasks are A) emotion intensity regres- sion (EI-REG): given a tweet and an emotion, de- termine the intensity of the emotion that best rep- resents the mental state of the tweeter, a real-value score between 0 and 1. B) Emotion intensity ordinal classification ∗corresponding author: sabino.miranda@infotec.mx (EI-OC): given a tweet and an emotion E, classify the tweet into one of four ordinal classes of inten- sity of emotion: anger, fear, joy, and sadness, that best represents the mental state of the tweeter. C) A sentiment intensity regression task (V-REG): given a tweet, determine the intensity of sentiment, a real-valued score between 0 (most negative) and 1 (most positive). D) A sentiment analysis, ordinal classification (V-OC): given a tweet, classify it into one of seven ordinal classes, corresponding to several levels of positive and negative sentiment intensity. In this context, one crucial step is the procedure used to transform the data (i.e., tweets) into the inputs (vectors) of the supervised learning tech- niques used. Typically, Natural Language Pro- cessing (NLP) approaches for data representation use n-grams of words, linguistic information such as dependency relations, syntactic information, lexical units (e.g., lemmas, stems), affective lexi- cons, error correction, etc. However, selecting the best configuration of those characteristics could be a cumbersome task, many times disregarded in favor of some well-known competitive setups. (Tellez et al., 2017b) studies the dependency be- tween the performance and the proper selection of the text model. This …

Content truncated to 500 words