# Social Content Moderation

A Twitter/X Platform spam classification model fine-tuned based on xlm-roberta-large, capable of identifying whether tweets are spam

A toxic comment classification model fine-tuned based on bert-base-uncased, used to identify toxic content in text.

This model improves online hate detection through dynamic dataset generation, focusing on learning from worst-case scenarios to enhance detection effectiveness.

A text classification model based on German DistilBERT for detecting toxic content in German comments