Summary of Deep Learning Based Cyberbullying Detection in Bangla Language, by Sristy Shidul Nath et al.
Deep Learning Based Cyberbullying Detection in Bangla Language
by Sristy Shidul Nath, Razuan Karim, Mahdi H. Miraz
First submitted to arxiv on: 7 Jan 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Social and Information Networks (cs.SI)
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 This study proposes a deep learning strategy for identifying cyberbullying in Bangla, a language with limited research in this domain. The authors use a dataset of 12282 versatile comments from multiple social media sites to develop a two-layer bidirectional long short-term memory (Bi-LSTM) model. The model is trained using various optimizers and validated through 5-fold cross-validation. The results show that the proposed model’s accuracy is high, with momentum-based stochastic gradient descent (SGD) achieving an accuracy of 94.46% and Adam optimizer achieving a F1 score of 95.23%. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Cyberbullying is a growing problem on social media platforms like Facebook, Twitter, and Instagram. It can have serious consequences for young people, causing emotional harm and even leading to depression or anxiety. In Bangla-speaking countries, there are few research studies on cyberbullying, which makes it harder to identify and prevent. This study aims to change that by developing a machine learning model that can detect cyberbullying in Bangla. The model uses a special type of neural network called Bi-LSTM to analyze comments from social media sites. By training the model with thousands of comments, researchers hope to create a tool that can quickly identify and report online bullying. |
Keywords
* Artificial intelligence * Deep learning * F1 score * Lstm * Machine learning * Neural network * Stochastic gradient descent
