Improving classifier training efficiency for automatic cyberbullying detection with Feature Density

DEA-RNN: A Hybrid Deep Learning Approach for Cyberbullying Detection in Twitter Social Media Platform

“…Besides, it forecasts the time interval that elapses between two neighboring comments. Eronen et al [53] suggested an approach for detecting cyberbullying based on the linguistically backed pre-processing and Feature Density (FD) approach. The authors investigated the effectiveness of FD utilizing linguistically-backed pre-processing such as stop words filtering, Parts of Speech (POS), Named Entity Recognition (NER), etc., approaches for assessing classification performance and the complexity of the dataset.…”

Transfer language selection for zero-shot cross-lingual abusive language detection

“…The experiments performed on actual cyberbullying data showed a major advantage of this approach to all previous methods, including the best performing method so far based on Brute Force Search algorithm. The method was later confirmed to also be useful in finding the best feature sets to be used in training to reduce the redundant experiment runs [36].…”

Identification of cyber harassment and intention of target users on social media platforms

“… Lopez-Vizcaíno et al (2021b) Supervised learning method Cyberbullying detection Vine social networks Textual Proposed dual clusters of features named threshold and dual for two early detection methods. Eronen et al (2021) Feature Density (FD) using different linguistically-backed feature pre-processing methods Automatic cyberbullying detection Social media Yelp business review Textual, Sentimental, Contextual To estimate dataset complexity Chia et al (2021) Feature Engineering techniques and Machine Learning To explore the irony and satire Twitter Textual, User-based To evaluate the properties of irony and sarcasm recognition in cyberbullying detection tasks. Ireland et al (2021) Supervised machine learning Automated detection and prevention systems Twitter Textual, Sentimental, User-based Bullies’ relative popularity, collective and automated efficacy, and incident interpretation Dennehy et al (2020) The Critical Appraisal Skills Program assessment tool Used to assess the calibre of the studies that were included.…”