# Social Media NLP

A large-scale pre-trained masked language model for Arabic dialects and Modern Standard Arabic, trained on 1 billion Arabic tweets

BERTweet is the first large-scale pretrained language model specifically designed for English tweets, trained on the RoBERTa architecture, suitable for social media text analysis.

This is a pre-trained language model based on the BERT-base architecture, specifically optimized for English tweets related to the 2020 US presidential election.