DeepAnalyzer at SemEval-2019 Task 6: A deep learning-based ensemble method for identifying offensive tweets

Proceedings of the 13th International Workshop on Semantic Evaluation (SemEval-2019), pages 582–586 Minneapolis, Minnesota, USA, June 6–7, 2019. ©2019 Association for Computational Linguistics 582 DeepAnalyzer at SemEval-2019 Task 6: A deep learning-based ensemble method for identifying offensive tweets Gretel Liz De la Pe˜na Sarrac´en and Paolo Rosso PRHLT Research Center, Universitat Polit`ecnica de Val`encia, Spain Abstract This paper describes the system we developed for SemEval 2019 on Identifying and Cate- gorizing Offensive Language in Social Media (OffensEval - Task 6). The task focuses on of- fensive language in tweets. It is organized into three sub-tasks for offensive language identi- fication; automatic categorization of offense types and offense target identification. The ap- proach for the first subtask is a deep learning- based ensemble method which uses a Bidirec- tional LSTM Recurrent Neural Network and a Convolutional Neural Network. Additionally we use the information from part-of-speech tagging of tweets for target identification and combine previous results for categorization of offense types. 1 Introduction The use of Internet has become an important me- dia of personal and commercial communication. In this scenario, some users take advantage of the anonymity of this kind of communication, using this to engage in behaviour that many of them would not consider in real life. Therefore, much of the offensive language is widespread in social networks. Then, studying offensive language in texts from the social media is an essential task for security, the prevention of cyber-bullying, among other abusive behavior. To increase the research in this areas, several workshops have been organized, such as ALW1 and TRAC2. Recently, OffensEval3 (Zampieri et al., 2019b), which is a shared task at the SemEval-20194 workshop has been launched on the research community. The aim of OffensE- val is to deal with offensive language detection in 1https://sites.google.com/site/abusivelanguageworkshop2017/ 2https://sites.google.com/view/trac1/home 3https://competitions.codalab.org/competitions/20011 4http://alt.qcri.org/semeval2019/index.php?id=tasks the English language focusing on messages from Twitter. In OffensEval, the treatment of offensive con- tent is divided into three subtasks taking the type and target of offenses into account: • A: Offensive language identification. • B: Automatic categorization of offense types. • C: Offense target identification. In this work, we present the methodology pro- posed to each of these sub-tasks, which includes an ensemble of a LSTM Recurrent Neural Net- work and a Convolutional Neural Network, and additionally linguistic features for the last two sub- tasks. The architecture of the system will be more detailed in the following sections. The paper is organized as follows. Next section briefly describes other works in this area. Then, Section 3 describes the proposed metodology and the dataset. Results are discussed in Section 4. Finally, we draw our conclusions together with a summary of our findings in Section 5. 2 Related Work Some approaches have been proposed to tackle the problem of offensive language detection. It is the case of recent works (Waseem et al., 2017; ElSherief et al., 2018; Gamb¨ack and Sikdar, 2017; Zhang et al., 2018) and surveys (Schmidt and Wie- gand, 2017) and (Fortuna and Nunes, 2018). There are even studies on …

Content truncated to 500 words