@inproceedings{akrah-pedersen-2023-duluthnlp,
    title = "{D}uluth{NLP} at {S}em{E}val-2023 Task 12: {A}fri{S}enti-{S}em{E}val: Sentiment Analysis for Low-resource {A}frican Languages using {T}witter Dataset",
    author = "Akrah, Samuel  and
      Pedersen, Ted",
    editor = {Ojha, Atul Kr.  and
      Do{\u{g}}ru{\"o}z, A. Seza  and
      Da San Martino, Giovanni  and
      Tayyar Madabushi, Harish  and
      Kumar, Ritesh  and
      Sartori, Elisa},
    booktitle = "Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval-2023)",
    month = jul,
    year = "2023",
    address = "Toronto, Canada",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2023.semeval-1.236/",
    doi = "10.18653/v1/2023.semeval-1.236",
    pages = "1697--1701",
    abstract = "This paper describes the DuluthNLP system that participated in Task 12 of SemEval-2023 on AfriSenti-SemEval: Sentiment Analysis for Low-resource African Languages using Twitter Dataset. Given a set of tweets, the task requires participating systems to classify each tweet as negative, positive or neutral. We evaluate a range of monolingual and multilingual pretrained models on the Twi language dataset, one among the 14 African languages included in the SemEval task. We introduce TwiBERT, a new pretrained model trained from scratch. We show that TwiBERT, along with mBERT, generally perform best when trained on the Twi dataset, achieving an F1 score of 64.29{\%} on the official evaluation test data, which ranks 14 out of 30 of the total submissions for Track 10. The TwiBERT model is released at \url{https://huggingface.co/sakrah/TwiBERT}"
}