@inproceedings{pado-2017-question,
    title = "Question Difficulty {--} How to Estimate Without Norming, How to Use for Automated Grading",
    author = "Pad{\'o}, Ulrike",
    editor = "Tetreault, Joel  and
      Burstein, Jill  and
      Leacock, Claudia  and
      Yannakoudakis, Helen",
    booktitle = "Proceedings of the 12th Workshop on Innovative Use of {NLP} for Building Educational Applications",
    month = sep,
    year = "2017",
    address = "Copenhagen, Denmark",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/W17-5001",
    doi = "10.18653/v1/W17-5001",
    pages = "1--10",
    abstract = "Question difficulty estimates guide test creation, but are too costly for small-scale testing. We empirically verify that Bloom{'}s Taxonomy, a standard tool for difficulty estimation during question creation, reliably predicts question difficulty observed after testing in a short-answer corpus. We also find that difficulty is mirrored in the amount of variation in student answers, which can be computed before grading. We show that question difficulty and its approximations are useful for \textit{automated grading}, allowing us to identify the optimal feature set for grading each question even in an unseen-question setting.",
}