RuG @ EVALITA 2018: Hate Speech Detection In Italian Social Media

Xiaoyu Bai, Flavio Merenda, Claudia Zaghi, Tomasso Caselli, Malvina Nissim

    Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademic

    1 Citation (Scopus)
    208 Downloads (Pure)

    Abstract

    We describe the systems the RuG Team developed in the context of the Hate Speech Detection Task in Italian Social Media at EVALITA 2018. We submitted a total of eight runs, participating in all four subtasks. The best macro-F1 score in all subtasks was obtained by a Linear SVM, using hate-rich embeddings. Our best system obtains competitive results, by rank- ing 6th (out of 14) in HaSpeeDe-FB, 3rd (out of 15) in HaSpeeDe-TW, 8th (out of 13) in Cross-HaSpeeDe FB, and 6th (out of 13) in Cross-HaSpeeDe TW.
    Original languageEnglish
    Title of host publicationSixth Evaluation Campaign of Natural Language Processing and Speech Tools for Italian
    Subtitle of host publicationFinal Workshop (EVALITA 2018)
    EditorsTommaso Caselli, Nicole Novielli, Viviana Patti, Paolo Rosso
    PublisherCEUR Workshop Proceedings (CEUR-WS.org)
    Number of pages5
    Publication statusPublished - 2018
    EventEVALITA 2018 - CLIC-It 2018, Turin, Italy
    Duration: 12-Dec-201813-Dec-2018

    Workshop

    WorkshopEVALITA 2018
    CountryItaly
    CityTurin
    Period12/12/201813/12/2018

    Keywords

    • hate speech
    • word embeddings
    • benchmark

    Cite this