@inproceedings{degraeuwe-2025-shall,
    title = "You Shall Know a Word{'}s Difficulty by the Family It Keeps: Word Family Features in Personalised Word Difficulty Classifiers for {L}2 {S}panish",
    author = "Degraeuwe, Jasper",
    editor = {Kochmar, Ekaterina  and
      Alhafni, Bashar  and
      Bexte, Marie  and
      Burstein, Jill  and
      Horbach, Andrea  and
      Laarmann-Quante, Ronja  and
      Tack, Ana{\"i}s  and
      Yaneva, Victoria  and
      Yuan, Zheng},
    booktitle = "Proceedings of the 20th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2025)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/landing_page/2025.bea-1.24/",
    pages = "312--325",
    ISBN = "979-8-89176-270-1",
    abstract = "Designing vocabulary learning activities for foreign/second language (L2) learners highly depends on the successful identification of difficult words. In this paper, we present a novel personalised word difficulty classifier for L2 Spanish, using the LexComSpaL2 corpus as training data and a BiLSTM model as the architecture. We train a base version (using the original LexComSpaL2 data) and a word family version of the classifier (adding word family knowledge as an extra feature). The base version obtains reasonably good performance (F1 = 0.53) and shows weak positive predictive power ({\ensuremath{\varphi}} = 0.32), underlining the potential of automated methods in determining vocabulary difficulty for individual L2 learners. The ``word family classifier'' is able to further push performance (F1 = 0.62 and {\ensuremath{\varphi}} = 0.45), highlighting the value of well-chosen linguistic features in developing word difficulty classifiers."
}