Ssn_nlp at SemEval 2020 Task 12: Offense Target Identification in Social Media Using Traditional and Deep Machine Learning Approaches

Proceedings of the 14th International Workshop on Semantic Evaluation, pages 2155–2160 Barcelona, Spain (Online), December 12, 2020. 2155 ssn nlp at SemEval-2020 Task 12: Offense Target Identification in Social Media using Traditional and Deep Machine Learning Approaches Thenmozhi D., Nandhinee PR, Arunima S, Amlan Sengupta Department of CSE, SSN College of Engineering, India theni d@ssn.edu.in {nandhinee16066,arunima17016,amlan17008}@cse.ssn.edu.in Abstract Offensive language identification (OLI) in user generated text is automatic detection of any profan- ity, insult, obscenity, racism or vulgarity that is addressed towards an individual or a group. Due to immense growth and usage of social media, it has an extensive reach and impact on the society. OLI is helpful for hate speech detection, flame detection and cyber bullying, hence it is used to avoid abuse and hurts. In this paper, we present state-of-the-art machine learning approaches for OLI. We follow several approaches which include classifiers like Naive Bayes, Support Vector Machine(SVM) and deep learning approaches like Recurrent Neural Network(RNN) and Masked LM (MLM). The approaches are evaluated on the OffensEval@SemEval2020 dataset and our team ssn nlp submitted runs for the third task of OffensEval shared task. The best run of ssn nlp that uses BERT (Bidirectional Encoder Representations from Transformers) for the purpose of training the OLI model obtained F1 score as 0.61 and it is our official submission. The model performs with an accuracy of 0.80 and an evaluation loss of 1.08. The model has a precision rate of 0.72 and a recall rate of 0.58. 1 Introduction In this day and age, offensive language is used predominantly in social media thereby giving rise to the need for more efficient and faster offensive language identification (OLI) algorithms. OLI is useful for several applications such as hate speech detection, flame detection, aggression detection and cyber bullying. Several workshops such as TA-COS1, TRAC2 (Kumar et al., 2018), Abusive Language Online3, ALW2 (Fiˇser et al., 2018) and GermEval (Wiegand et al., 2018) have been organized recently in this area of research. In this line, OffensEval@SemEval2020 (Zampieri et al., 2020) shared task focuses on Multilingual Offensive Language Identification in Social Media. It consists of three subtasks namely offensive language detection, categorization of offensive language and offensive language target identification. Sub Task A aims to detect text as offensive (OFF) or not offensive (NOT). Sub Task B aims to classify the offensive type as targeted text (TIN) or untargeted text (UNT). Sub Task C focuses on identifying the target of tweet as individual (IND), group (GRP) or others (OTH). Our team ssn nlp participated in the third subtask of Multilingual Offensive Language Identification in Social Media. 2 Related Work A lot of research has been reported in the field of Offensive Language Identification. Wiegand et al. (2018) presented an overview of GermEval shared task on the identification of offensive language that focused on the classification of German tweets from Twitter. A dataset of over 8,500 annotated tweets was provided for a coarse-grained binary classification task in which systems were trained to discriminate between offensive and …

Content truncated to 500 words