Summary of The Use Of a Large Language Model For Cyberbullying Detection, by Bayode Ogunleye et al.
The Use of a Large Language Model for Cyberbullying Detection
by Bayode Ogunleye, Babitha Dharmaraj
First submitted to arxiv on: 6 Feb 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Applications (stat.AP)
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 The proposed paper explores the application of large language models like BERT and RoBERTa for detecting cyberbullying in online forums, blogs, and social media platforms. The dominance of social media has amplified bullying channels, making it a severe threat to mental and physical health. Current machine learning algorithms struggle due to high class imbalance and generalisation issues. The study prepares a new dataset (D2) from existing studies (Formspring and Twitter) and demonstrates that RoBERTa outperformed other models on datasets D1 and D2. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Cyberbullying is a big problem online! It can hurt people’s feelings and even make them feel sad or scared. Right now, there are ways to stop mean messages from getting shared online. Scientists are working on new ideas to help prevent this kind of behavior. They took existing data from two websites (Formspring and Twitter) and made a new dataset to test their ideas. They found that one special model called RoBERTa did really well at stopping cyberbullying. |
Keywords
* Artificial intelligence * Bert * Machine learning
