JU_ETCE_17_21 at SemEval-2019 Task 6: Efficient Machine Learning and Neural Network Approaches for Identifying and Categorizing Offensive Language in Tweets

Proceedings of the 13th International Workshop on Semantic Evaluation (SemEval-2019), pages 662–667 Minneapolis, Minnesota, USA, June 6–7, 2019. ©2019 Association for Computational Linguistics 662 JU ETCE 17 21 at SemEval-2019 Task 6: Efficient Machine Learning and Neural Network Approaches for Identifying and Categorizing Offensive Language in Tweets Mainak Pal*, Preeti Mukherjee∗, Somnath Banerjee, Sudip Kumar Naskar Jadavpur University, Kolkata, India {mainak.pal08,preetimukherjee08,sb.cse.ju}@gmail.com sudip.naskar@cse.jdvu.ac.in Abstract This paper describes our system submissions as part of our participation (team name: JU ETCE 17 21) in the SemEval 2019 shared task 6: “OffensEval: Identifying and Catego- rizing Offensive Language in Social Media”. We participated in all the three sub-tasks: i) Sub-task A: offensive language identification, ii) Sub-task B: automatic categorization of of- fense types, and iii) Sub-task C: offense target identification. We employed machine learn- ing as well as deep learning approaches for the sub-tasks. We employed Convolutional Neural Network (CNN) and Recursive Neu- ral Network (RNN) Long Short-Term Memory (LSTM) with pre-trained word embeddings. We used both word2vec and Glove pre-trained word embeddings. We obtained the best F1- score using CNN based model for sub-task A, LSTM based model for sub-task B and Lo- gistic Regression based model for sub-task C. Our best submissions achieved 0.7844, 0.5459 and 0.48 F1-scores for sub-task A, sub-task B and sub-task C respectively. 1 Introduction Today, very large amounts of information are available in online documents. As part of the ef- fort to better organize this information for users, researchers have been actively investigating the problem of automatic text categorization. Tweets are short length pieces of text, usually writ- ten in informal style that contain abbreviations, misspellings and creative syntax (like emoticons, hashtags etc). In this paper we show that our ∗These two authors have contributed equally multi-view ensemble approach that leverages sim- ple representations of texts may achieve good re- sults in the task of message polarity classification. We used different machine learning algorithm and neural network approaches for all the tasks which are explained in the subsequent sections. The pa- per is organized as follows: Section 2 lists down the related work and Section 3 describes our ap- proach. Section 4 presents the experiments, results on the development set and discussion about the confusion matrix and Section 5 details about the observation. Section 6 concludes the paper with possible future work. OffensEval@SemEval-2019 shared task de- scription, data and results are described in the overview paper (Zampieri et al., 2019b). 2 Related Work Papers published in the last two years include the surveys by (Schmidt and Wiegand, 2017) and (Fortuna and Nunes, 2018), the paper by (Davidson et al., 2017) presenting the Hate Speech Detection dataset used in (Malmasi and Zampieri, 2017) and a few other recent papers such as (ElSherief et al., 2018; Gamb¨ack and Sikdar, 2017; Zhang et al., 2018). A proposal of typology of abusive language sub-tasks is presented in (Waseem et al., 2017). For studies on languages other than English see (Su et al., 2017) on Chinese and (Fiˇser et al., 2017) on …

Content truncated to 500 words