Source-driven Representations for Hate Speech Detection

Flavio Merenda, Claudia Zaghi, Tomasso Caselli, Malvina Nissim

    OnderzoeksoutputAcademicpeer review

    236 Downloads (Pure)

    Samenvatting

    Sources, in the form of selected Facebook pages, can be used as indicators of hate-rich content. Polarized distributed representations created over such content prove superior to generic embeddings in the task of hate speech detection. The same content seems to carry a too weak signal to proxy silver labels in a distant supervised setting. However, this signal is stronger than gold labels which come from a different distribution, leading to re-think the process of annotation in the context of highly subjective judgments.
    Originele taal-2English
    TitelProceedings of the Fifth Italian Conference on Computational Linguistics (CLiC-it 2018)
    RedacteurenTomasso Caselli, Nicole Noviell, Viviana Patti, Paolo Rosso
    Aantal pagina's6
    StatusPublished - 2018
    EvenementEVALITA 2018 - CLIC-It 2018, Turin, Italy
    Duur: 12-dec-201813-dec-2018

    Publicatie series

    Naam
    Volume2253
    ISSN van elektronische versie1613-0073

    Workshop

    WorkshopEVALITA 2018
    LandItaly
    StadTurin
    Periode12/12/201813/12/2018

    Citeer dit