Identification of online harassment using ensemble fine-tuned pre-trained Bert

Abstract

Identification of online hate is the prime concern for natural language processing researchers; social media has augmented this menace by providing a virtual platform for online harassment. This study identifies online harassment using the trolling aggression and cyber-bullying dataset from shared tasks workshop. This work concentrates on extreme pre-processing and ensemble approach for model building; this study also considers the existing algorithms like the random forest, logistic regression, multinomial Naïve Bayes. Logistic regression proves to be more efficient with the highest accuracy of 57.91%. Ensemble bidirectional encoder representation from transformers showed promising results with 62% precision, which is better than most existing models.

Exploring noise-induced techniques to strengthen deep learning model resilience

“…In recent years, noise-induced regularization has emerged as a promising strategy to bolster model generalization. Neelakantan et al [5] pioneered the concept of adding gradient noise, enhancing the learning dynamics of deep networks [13]. Vincent et al [8] proposed denoising autoencoders, which learn robust features by reconstructing clean inputs from noisy data.…”