@inproceedings{gombar-etal-2017-debunking,
    title = "Debunking Sentiment Lexicons: A Case of Domain-Specific Sentiment Classification for {C}roatian",
    author = "Gombar, Paula  and
      Medi{\'c}, Zoran  and
      Alagi{\'c}, Domagoj  and
      {\v{S}}najder, Jan",
    editor = "Erjavec, Toma{\v{z}}  and
      Piskorski, Jakub  and
      Pivovarova, Lidia  and
      {\v{S}}najder, Jan  and
      Steinberger, Josef  and
      Yangarber, Roman",
    booktitle = "Proceedings of the 6th Workshop on {B}alto-{S}lavic Natural Language Processing",
    month = apr,
    year = "2017",
    address = "Valencia, Spain",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/add-emnlp-2024-awards/W17-1409/",
    doi = "10.18653/v1/W17-1409",
    pages = "54--59",
    abstract = "Sentiment lexicons are widely used as an intuitive and inexpensive way of tackling sentiment classification, often within a simple lexicon word-counting approach or as part of a supervised model. However, it is an open question whether these approaches can compete with supervised models that use only word-representation features. We address this question in the context of domain-specific sentiment classification for Croatian. We experiment with the graph-based acquisition of sentiment lexicons, analyze their quality, and investigate how effectively they can be used in sentiment classification. Our results indicate that, even with as few as 500 labeled instances, a supervised model substantially outperforms a word-counting model. We also observe that adding lexicon-based features does not significantly improve supervised sentiment classification."
}