When the Timeline Meets the Pipeline: A Survey on Automated Cyberbullying Detection

Abstract

Web 2.0 helped user-generated platforms to spread widely. Unfortunately, it also allowed for cyberbullying to spread. Cyberbullying has negative effects that could lead to cases of depression and low self-esteem. It has become crucial to develop tools for automated cyberbullying detection. The research on developing these tools has been growing over the last decade, especially with the recent advances in machine learning and natural language processing. Given the large body of work on this topic, it is vital to critically review the literature on cyberbullying within the context of these latest advances. In this paper, we conduct a survey on the automated detection of cyberbullying. Our survey sheds light on some challenges and limitations for the field. The challenges range from defining cyberbullying, data collection and feature representation to model selection, training and evaluation. We also provide some suggestions for improving the task of cyberbullying detection. In addition to the survey, we propose to improve the task of cyberbullying detection by addressing some of the raised limitations: 1) Using recent contextual language models like BERT for the detection of cyberbullying; 2) Using slang-based word embeddings to generate better representations of the cyberbullying-related datasets. Our results show that BERT outperforms state-of-the-art cyberbullying detection models and deep learning models. The results also show that deep learning models initialised with slang-based word embeddings outperform deep learning models initialised with traditional word embeddings.

Cyberbullying Classifiers are Sensitive to Model-Agnostic Perturbations

“…This experiment not only underlines the strong focus on lexical cues 13 from linear classifiers, but also that transformer models are not immune to lexical variation-even when candidates are sampled from their own language model. This provides further evidence in line with research from Elsafoury et al (2021a), and Elsafoury et al (2021b) (see Section 5). Semantic Consistency of Samples Here, we compared X pos with X pos as a reference.…”

“…We follow recent state-of-the-art results (Elsafoury et al, 2021a) for our main classification model, and finetune all BERT-based models for 10 epochs with a batch size of 32 and a learning rate of 2e−5, as suggested by Devlin et al (2019). Accordingly, we set the maximum sequence length to 128, and insert a single linear layer after the pooled output.…”

“…), or re-training (Caselli et al, 2020) BERT. It is worth noting that Elsafoury et al (2021a;Elsafoury et al (2021b) show that although fine-tuning BERT achieves state-of-theart performance in classification, its attention scores do not correlate with cyberbullying features, and they expect generalization of such models to be subpar. In our experiments, we employ similar domain-specific fine-tuned BERT models, and gauge generalization, sensitivity to perturbations, and the effects of augmentation to potentially improve the former.…”

Building towards Automated Cyberbullying Detection: A Comparative Analysis

“…Tripathy et al [ 37 ] used fine-tuned ALBERT model for cyberbullying detection by using ALBERT-large, a larger pretraining corpus over the BERT-Base that Mozafari et al [ 34 ] implemented. Elsafoury et al [ 13 ] conducted experiments using BERT for cyberbullying detection in comparison to the DL models used in the literature. The results of their experiments found that using BERT improved the detection, and they found that there is lack of research on the use of BERT for cyberbullying detection.…”

“…Rosa et al [ 12 ] conducted an analysis by performing quantitative systematic review of 22 studies on automatic cyberbullying detection. Elsafoury et al [ 13 ] also presented a systematic review by reviewing the literature on automated cyberbullying detection and identifying the limitations in the available works. They also conducted experiments on the limitations they identified on the available automated cyberbullying detection and investigated their impact on the performance of cyberbullying detection.…”