@inproceedings{aguero-torales-etal-2021-logistical,
    title = "On the logistical difficulties and findings of Jopara Sentiment Analysis",
    author = {Ag{\"u}ero-Torales, Marvin  and
      Vilares, David  and
      L{\'o}pez-Herrera, Antonio},
    editor = "Solorio, Thamar  and
      Chen, Shuguang  and
      Black, Alan W.  and
      Diab, Mona  and
      Sitaram, Sunayana  and
      Soto, Victor  and
      Yilmaz, Emre  and
      Srinivasan, Anirudh",
    booktitle = "Proceedings of the Fifth Workshop on Computational Approaches to Linguistic Code-Switching",
    month = jun,
    year = "2021",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2021.calcs-1.12/",
    doi = "10.18653/v1/2021.calcs-1.12",
    pages = "95--102",
    abstract = "This paper addresses the problem of sentiment analysis for Jopara, a code-switching language between Guarani and Spanish. We first collect a corpus of Guarani-dominant tweets and discuss on the difficulties of finding quality data for even relatively easy-to-annotate tasks, such as sentiment analysis. Then, we train a set of neural models, including pre-trained language models, and explore whether they perform better than traditional machine learning ones in this low-resource setup. Transformer architectures obtain the best results, despite not considering Guarani during pre-training, but traditional machine learning models perform close due to the low-resource nature of the problem."
}