naija-twitter-sentiment-afriberta-large is the first multilingual twitter sentiment classification model for four (4) Nigerian languages (Hausa, Igbo, Nigerian Pidgin, and Yorùbá) based on a fine-tuned castorini/afriberta_large large model. It achieves the state-of-the-art performance for the twitter sentiment classification task trained on the NaijaSenti corpus. The model has been trained to classify tweets into 3 sentiment classes: negative, neutral and positive Specifically, this model is a xlm-roberta-large model that was fine-tuned on an aggregation of 4 Nigerian language datasets obtained from NaijaSenti dataset.