Human Language Technologies Project for the Academic Year 2023-2024
-
Updated
Aug 21, 2024 - Jupyter Notebook
Human Language Technologies Project for the Academic Year 2023-2024
Cyber Bullying Detection ML Model (CBD.ML)
Identifying trolling, aggression, cyber-bullying and hate speech etc. Three classes: Overtly Aggressive (OAG), Covertly Aggressive (CAG), and Non-aggressive (NAG)
Successfully fine-tuned a pretrained DistilBERT transformer model that can classify social media text data into one of 4 cyberbullying labels i.e. ethnicity/race, gender/sexual, religion and not cyberbullying with a remarkable accuracy of 99%.
Cyber bullying detection in Twitter using machine learning
Code and data for the paper "Politeness Stereotypes and Attack Vectors: Gender Stereotypes in Japanese and Korean Language Models" (Arxiv 2023)
Sentinel adalah proyek kelompok kami yang bertujuan untuk mendeteksi dan mengklasifikasikan komentar di media sosial, khususnya untuk mengidentifikasi apakah sebuah komentar termasuk kategori bullying atau non-bullying.
Research paper about Cyber Bulluying Detection on Twitter from Stanford University students
classify text data into different cyberbullying categories.
Natural Language Processor ecosystem for proactive and reactive cyberbullying response | Created during Hack4Lem 2021 hackathon
Cyberbullying Detection App tailored for the Arabic language. The app is designed to identify instances of cyberbullying in Arabic text using various machine learning and deep learning algorithms.
This application can detect the hate and toxic tweets of users amongst an entire corpora of tweets and thus can be an effective methodology towards reducing cyber bullying.
This repository is comprised of files that contributed, one way or another, to the creation of the project entitled, "Quickgarde: A Plug-in for Detecting Cyberbullying Occurrences in Filipino Social Media Posts
In this paper, we have implemented SVM, Bayesian and CNN, LSTM Neural network models for cyber bullying detection using Azure ML studio and compared their results.