NLP_Passau at SemEval-2020 Task 12: Multilingual Neural Network for Offensive Language Detection in English, Danish and Turkish

Proceedings of the 14th International Workshop on Semantic Evaluation, pages 2090–2097 Barcelona, Spain (Online), December 12, 2020. 2090 NLP_Passau at SemEval-2020 Task 12: Multilingual Neural Network for Offensive Language Detection in English, Danish and Turkish Omar Hussein, Hachem Sfar, Jelena Mitrovi´c, Michael Granitzer Faculty of Computer Science and Mathematics, University of Passau, Germany {hussei05|sfar01}@ads.uni-passau.de {jelena.mitrovic|michael.granitzer}@uni-passau.de Abstract This paper describes a neural network (NN) model that was used for participating in the OffensEval, Task 12 of the SemEval 2020 workshop. The aim of this task is to identify offensive speech in social media, specifically in tweets. The model we used, C-BiGRU, is composed of a Convolutional Neural Network (CNN) along with a bidirectional Recurrent Neural Network (RNN). A multi- dimensional numerical representation (embedding) for each of the words in the tweets, that were used by the model, was determined using fastText. This was utilized with a dataset of labeled tweets to train the model on detecting combinations of words that may convey an offensive meaning. The model was then used in the sub-task A of the English, Turkish and Danish competitions of the workshop, achieving F1 scores of 90.88%, 76.76% and 76.70%, respectively. 1 Introduction With around 3.08 billion users in 2020, the number of social media users is continuing to grow. One of the most important features of social media is the presence of user generated content such as photos, videos or texts (Obar and Wildman, 2015). The reliance on user generated content, however, presents a significant challenge in moderating such content which has the potential to instigate violence within communities in real life, if it contains hate-speech (Laub, 2019). There has been growing interest from social media companies, fueled by the pressure from the government agencies, to detect and try to block such harmful content as in some cases it could lead the platform on which the content was distributed into paying significant fines (Deutsche-Welle, 2019). Furthermore, using computer algorithms to automatically detect any content that could contain hateful inclinations is a challenging task that has also attracted the attention of the scientific community as can be seen by various workshops, competitions and conferences in recent years: TRAC (Kumar et al., 2018), EVALITA hate-speech detection task (Cristina et al., 2018), GermEval (Wiegand et al., 2018), (Fersini et al., 2018) and HatEval (Basile et al., 2019). The most prominent effort in this regard has been the OffensEval challenge (Zampieri et al., 2019), which sees its second edition this year as the 12th task of SemEval, Multilingual Offensive Language Iden- tification in Social Media, or OffensEval 2 (Zampieri et al., 2020).The Offensive Language Identification Dataset or OLID which consists of a collection of 14,200 English tweets with three levels of annotation for each of them is provided. The first level of annotation identifies whether a tweet contains offensive language or not, which is the aim of Sub-task A. The second level determines the type of offensive language in the tweet which is the focus of Sub-task B, and lastly Sub-task C …

Content truncated to 500 words