INGEOTEC at SemEval-2019 Task 5 and Task 6: A Genetic Programming Approach for Text Classification

Proceedings of the 13th International Workshop on Semantic Evaluation (SemEval-2019), pages 639–644 Minneapolis, Minnesota, USA, June 6–7, 2019. ©2019 Association for Computational Linguistics 639 INGEOTEC at SemEval-2019 Task 5 and Task 6: A Genetic Programming Approach for Text Classification 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 HatEval and OffensEval challenges for En- glish and Spanish languages. We used several approaches, B4MSA, FastText, and EvoMSA. Best results were achieved with EvoMSA, which is a multilingual and domain- independent architecture that combines the prediction from different knowledge sources to solve text classification problems. 1 Introduction Social media platforms, like Twitter and Face- book, are spaces where people interact with oth- ers and express themselves; while these plat- forms encourage free speech, other issues could emerge such as the usage of offensive language that could mock or insult individuals or groups of people. Thus, detecting offenses and misbehav- ior expressed in text form is interesting to measure the people’s feelings and warn them about pos- sible attacks on others such as abusive language, hate speech, cyberbullying, trolling, among others (Waseem et al., 2017). In order to tackle these text classifications prob- lems, SemEval-2019 proposed two tasks: mul- tilingual detection of hate speech against immi- grants and women in Twitter HatEval, task 5 (Basile et al., 2019), and identification and cate- gorization of offensive language in social media OffensEval, task 6 (Zampieri et al., 2019b). In this paper, we present the results from our participating in these two tasks. The HatEval challenge consists in detecting hate speech for two targets, immigrants and women, in Twitter for Spanish and English lan- guages. There are two subtasks, subtask A is a bi- nary classification where systems have to predict whether a tweet with a given target (immigrants or women) is hateful or not hateful; subtask B is about aggressive behavior and target classification, systems are asked to classify hateful tweets as ag- gressive or not aggressive, and identify the target harassed (individual or group). On the other hand, OffensEval challenge con- sists in determining if a given message has offen- sive content. It is divided into three subtasks. Sub- task A is dedicated to identifying the offensive lan- guage, i.e., determine if a message is offensive or not offensive. Subtask B is about categorizing of- fense types; that is, a tweet containing an insult or threat to someone, or a tweet containing non- targeted profanity and swearing. Finally, subtask C focus on identifying the target, i.e., whether the offensive post is about an individual, a group, or others. Both HatEval and OffensEval are related tasks to abusive language, Waseem et al. (Waseem et al., 2017) describe tasks on this theme; authors focus their analysis on two primary factors that could guide the modeling of systems: i) language is di- rected towards a specific individual, entity, or gen- eralized group; ii) the abusive content …

Content truncated to 500 words