@inproceedings{dukic-etal-2025-characterizing,
    title = "Characterizing Linguistic Shifts in {C}roatian News via Diachronic Word Embeddings",
    author = "Duki{\'c}, David  and
      Bari{\'c}, Ana  and
      {\v{C}}uljak, Marko  and
      Juki{\'c}, Josip  and
      Tutek, Martin",
    editor = "Piskorski, Jakub  and
      P{\v{r}}ib{\'a}{\v{n}}, Pavel  and
      Nakov, Preslav  and
      Yangarber, Roman  and
      Marcinczuk, Michal",
    booktitle = "Proceedings of the 10th Workshop on Slavic Natural Language Processing (Slavic NLP 2025)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/acl25-workshop-ingestion/2025.bsnlp-1.13/",
    pages = "108--115",
    ISBN = "978-1-959429-57-9",
    abstract = "Measuring how semantics of words change over time improves our understanding of how cultures and perspectives change. Diachronic word embeddings help us quantify this shift, although previous studies leveraged substantial temporally annotated corpora. In this work, we use a corpus of 9.5 million Croatian news articles spanning the past 25 years and quantify semantic change using skip-gram word embeddings trained on five-year periods. Our analysis finds that word embeddings capture linguistic shifts of terms pertaining to major topics in this timespan (COVID-19, Croatia joining the European Union, technological advancements). We also find evidence that embeddings from post-2020 encode increased positivity in sentiment analysis tasks, contrasting studies reporting a decline in mental health over the same period."
}