Foul at SemEval-2023 Task 12: MARBERT Language model and lexical filtering for sentiments analysis of tweets in Algerian Arabic

This paper describes the system we designed for our participation in SemEval-2023 Task 12 Track 6 about Algerian dialect sentiment analysis. We propose a transformer language model approach combined with a lexicon mixing terms and emojis which is used in a postprocessing filtering stage. The Algerian sentiment lexicons were extracted manually from tweets. We report on our experiments on the Algerian dialect, where we compare the performance of MARBERT to the one of ArabicBERT and CAMeLBERT on the training and development datasets of Task 12. We also analyze the contribution of our post-processing lexical filtering for sentiment analysis. Our system obtained an F1 score equal to 70%, ranking 9th among 30 participants.