Sonal.kumari at SemEval-2020 Task 12: Social Media Multilingual Offensive Text Identification and Categorization Using Neural Network Models

Proceedings of the 14th International Workshop on Semantic Evaluation, pages 2146–2154 Barcelona, Spain (Online), December 12, 2020. 2146 Sonal.kumari at SemEval-2020 Task 12: Social Media Multilingual Of- fensive Text Identification and Categorization using Neural Network Models Sonal Kumari Samsung Research Institute, Bangalore, India sonal.kumari@samsung.com Abstract In this paper, we present our approaches and results for SemEval-2020 Task 12, Multilingual Offensive Language Identification in Social Media (OffensEval 2020). The OffensEval 2020 had three subtasks: A) Identifying the tweets to be offensive (OFF) or non-offensive (NOT) for Arabic, Danish, English, Greek, and Turkish languages, B) Detecting if the offensive tweet is targeted (TIN) or untargeted (UNT) for the English language, and C) Categorizing the offensive targeted tweets into three classes, namely: individual (IND), Group (GRP), or Other (OTH) for the English language. We participate in all the subtasks A, B, and C. In our solution, first we use the pre-trained BERT model for all subtasks, A, B, and C and then we apply the BiLSTM model with attention mechanism (Attn-BiLSTM) for the same. Our result demonstrates that the pre- trained model is not giving good results for all types of languages and is compute and memory intensive whereas the Attn-BiLSTM model is fast and gives good accuracy with fewer re- sources. The Attn-BiLSTM model is giving better accuracy for Arabic and Greek where the pre- trained model is not able to capture the complete context of these languages due to lower vocab- size. 1 Introduction The usage of offensive language in social media is very common nowadays. Sometimes it is used for fun and entertainment purposes, but sometimes it is an expression of user’s aggression, hate, and/or offensive behavior. Identification of user’s intention with an offensive content on social media requires domain-specific sentiment analysis at fined-grained level of granularity. To control the offensive behav- ior of the user’s post on social media requires the categorization of hate speech problems into new no- tions like abusive, aggressive, and/or offensive hate speech. Such categorization helps law-enforcement agencies for the surveillance of social media. Identification of hate, aggression, or offensive speech in user-generated content has attracted signifi- cant attention in the sentiment analysis research area recently. As evidenced, in recent publications (Waseem et al. 2016; Davidson et al., 2017, Malmasi and Zampieri, 2018, Kumar et al. 2018) and work- shops such as AWL and TRAC and competitions such as HatEval 2019 (Basile et al. 2019), HASOC 2019, and OffensEval 2019 (Zampieri et al. 2019). The exponential rise of users on social media and their posts on social media led to an enormous amount of data generation. Detection of hate, offensive speech, aggression, or abusive content on social media requires the involvement of algorithms to make decisions based on deep learning models such as LSTM, Bidirectional LSTM, pre-trained BERT (Bidirectional Encoder Representations from Trans- formers), CNN, or Stacked CNN, but not limited. The OffensEval-2020 has been introduced as a Multilingual Offensive Language Identification by Zampieri et al. (2020) in which following 3 subtasks were given: (A) …

Content truncated to 500 words