Performance analysis of Word Embeddings for Cyberbullying Detection
Subbaraju Pericherla, E. Ilavarasan
Abstract
Abstract Cyber bullying activities are increasing day by day with the increase of Social Media Platforms such as Face book, Twitter, Instagram etc. Bullies take the advantage of these large online connected platforms due to which it became as a big challenging task in Natural Language Processing (NLP). In this paper, we compare the performance of various word embedding methods from basic word embedding methods to recent advanced language models such as RoBERTa, XLNET, ALBERT, etc. for cyberbullying detection. We used LightGBM and Logistic regression classifiers for the classification of bullying and non-bullying tweets. Among all the models, RoBERTa is outperformed as compared to state-of-the-art models.
Topics & Concepts
Word embeddingTask (project management)Computer scienceWord (group theory)Social mediaEmbeddingNatural language processingLogistic regressionArtificial intelligenceRandom forestFace (sociological concept)Speech recognitionMachine learningLinguisticsWorld Wide WebEngineeringSystems engineeringPhilosophyHate Speech and Cyberbullying DetectionSoftware Engineering ResearchBullying, Victimization, and Aggression