Detection of Cyberbullying on Social Media Platforms Using Machine Learning

Cyberbullying is a prominent issue that affects many people within their lifetime. In this paper we explore the use of Machine Learning (ML) and Natural Language Processing (NLP) techniques to support automatic detection of cyberbullying. The paper discusses first the significance of cyberbullying and its relationship to cybersecurity. Then, in order to illustrate the automatic detection approach and its integration into a web application, we considered a benchmark dataset, the Offensive Language Identification Dataset (OLID). This is an annotated large-scale dataset with approximate 14,000 English tweets, that was used in various works for detecting offensive posts in social media, predicting their type and target. To solve the classification problems associated with OLID dataset, nine supervised models were developed for each task of the dataset. We used the TFIDF (Term Frequency Inverse Document Frequency) feature selection and GridSearchCV to find the optimum parameters for each of the ML algorithms. Evaluation metrics, such as build time, accuracy, precision, recall, and F1-score were used to compare the ML techniques. The Random Forest models achieved 82, 90, and 61% in accuracy for the tasks associated with the dataset, which were the best performing algorithms supported by the other metrics. The Random Forest models that achieved the best performance, were integrated within a Flask web application, publicly available. This serves as proof of concept, allowing users to test the classifier. The paper explains how a developed ML model can be integrated into a web application. Furthermore, one can develop an API for handling larger and more frequent data requests or integrate in a social media platform the classifier.