bertmodel

A dataset of 3+ million posts from 1025 far-right Telegram channels (2019-2024), including a ready-to-use BERTopic analysis for thematic exploration.

Natural Language Processing

This project is designed to classify YouTube comments as toxic or non-toxic using BERT (Bidirectional Encoder Representations from Transformers). By fine-tuning a pre-trained BERT model, we leverage state-of-the-art NLP capabilities to identify harmful content in online conversations.

Generate insights and rankings for potential candidates