@inproceedings{ohman-etal-2020-xed,
    title = "{XED}: A Multilingual Dataset for Sentiment Analysis and Emotion Detection",
    author = {{\"O}hman, Emily  and
      P{\`a}mies, Marc  and
      Kajava, Kaisla  and
      Tiedemann, J{\"o}rg},
    editor = "Scott, Donia  and
      Bel, Nuria  and
      Zong, Chengqing",
    booktitle = "Proceedings of the 28th International Conference on Computational Linguistics",
    month = dec,
    year = "2020",
    address = "Barcelona, Spain (Online)",
    publisher = "International Committee on Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2020.coling-main.575/",
    doi = "10.18653/v1/2020.coling-main.575",
    pages = "6542--6552",
    abstract = "We introduce XED, a multilingual fine-grained emotion dataset. The dataset consists of human-annotated Finnish (25k) and English sentences (30k), as well as projected annotations for 30 additional languages, providing new resources for many low-resource languages. We use Plutchik`s core emotions to annotate the dataset with the addition of neutral to create a multilabel multiclass dataset. The dataset is carefully evaluated using language-specific BERT models and SVMs to show that XED performs on par with other similar datasets and is therefore a useful tool for sentiment analysis and emotion detection."
}