Summary of Deep Learning Approaches For Detecting Adversarial Cyberbullying and Hate Speech in Social Networks, by Sylvia Worlali Azumah et al.
Deep Learning Approaches for Detecting Adversarial Cyberbullying and Hate Speech in Social Networks
by Sylvia Worlali Azumah, Nelly Elsayed, Zag ElSayed, Murat Ozer, Amanda La Guardia
First submitted to arxiv on: 30 May 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Computation and Language (cs.CL); Computers and Society (cs.CY)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary In this paper, researchers tackle cyberbullying in social media text data by developing a deep learning-based approach to detect hate speech. They focus on detecting malicious content using a correction algorithm, yielding impressive results. Specifically, an LSTM model with 100 epochs achieved high accuracy (87.57%), precision (88.73%), recall (87.57%), F1-score (88.15%), and AUC-ROC score (91%). This paper outperforms previous studies, offering a solution to enhance digital environment safety. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Cyberbullying is a big problem on the internet. Researchers are trying to make online spaces safer by detecting mean language and hate speech. But some bad actors try to trick these detection systems. In this paper, scientists developed a new way to detect mean messages using deep learning. They tested it on social media text data and got great results. The method was super accurate (87.57%) and better than others before it. |
Keywords
» Artificial intelligence » Auc » Deep learning » F1 score » Lstm » Precision » Recall
