@inproceedings{bear-etal-2020-tuemix,
    title = "{T}ue{M}ix at {S}em{E}val-2020 Task 9: Logistic Regression with Linguistic Feature Set",
    author = "Bear, Elizabeth  and
      Hoefels, Diana Constantina  and
      Manolescu, Mihai",
    editor = "Herbelot, Aurelie  and
      Zhu, Xiaodan  and
      Palmer, Alexis  and
      Schneider, Nathan  and
      May, Jonathan  and
      Shutova, Ekaterina",
    booktitle = "Proceedings of the Fourteenth Workshop on Semantic Evaluation",
    month = dec,
    year = "2020",
    address = "Barcelona (online)",
    publisher = "International Committee for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2020.semeval-1.178/",
    doi = "10.18653/v1/2020.semeval-1.178",
    pages = "1316--1321",
    abstract = "Commonly occurring in settings such as social media platforms, code-mixed content makes the task of identifying sentiment notably more challenging and complex due to the lack of structure and noise present in the data. SemEval-2020 Task 9, SentiMix, was organized with the purpose of detecting the sentiment of a given code-mixed tweet comprising Hindi and English. We tackled this task by comparing the performance of a system, TueMix - a logistic regression algorithm trained with three feature components: TF-IDF n-grams, monolingual sentiment lexicons, and surface features - with a neural network approach. Our results showed that TueMix outperformed the neural network approach and yielded a weighted F1-score of 0.685."
}