@article{opitz-2024-closer,
    title = "A Closer Look at Classification Evaluation Metrics and a Critical Reflection of Common Evaluation Practice",
    author = "Opitz, Juri",
    journal = "Transactions of the Association for Computational Linguistics",
    volume = "12",
    year = "2024",
    address = "Cambridge, MA",
    publisher = "MIT Press",
    url = "https://preview.aclanthology.org/add-emnlp-2024-awards/2024.tacl-1.46/",
    doi = "10.1162/tacl_a_00675",
    pages = "820--836",
    abstract = "Classification systems are evaluated in a countless number of papers. However, we find that evaluation practice is often nebulous. Frequently, metrics are selected without arguments, and blurry terminology invites misconceptions. For instance, many works use so-called {\textquoteleft}macro' metrics to rank systems (e.g., {\textquoteleft}macro F1') but do not clearly specify what they would expect from such a {\textquoteleft}macro' metric. This is problematic, since picking a metric can affect research findings and thus any clarity in the process should be maximized. Starting from the intuitive concepts of bias and prevalence, we perform an analysis of common evaluation metrics. The analysis helps us understand the metrics' underlying properties, and how they align with expectations as found expressed in papers. Then we reflect on the practical situation in the field, and survey evaluation practice in recent shared tasks. We find that metric selection is often not supported with convincing arguments, an issue that can make a system ranking seem arbitrary. Our work aims at providing overview and guidance for more informed and transparent metric selection, fostering meaningful evaluation."
}