Bäumler, JulianKaufhold, Marc-AndréVoronin, GeorgReuter, Christian2024-08-212024-08-212024https://dl.gi.de/handle/20.500.12116/44267In Germany, both law enforcement agencies and dedicated reporting centers engage in various activities to counter illegal online hate speech. Due to the high volume of such content and against the background of limited resources, their personnel can be confronted with the issue of information overload. To mitigate this issue, technologies for information filtering, classification, prioritization, and visualization offer great potential. However, domain-specific classification schemes that differentiate subtypes of online hate speech are a prerequisite for the development of such assistive tools. There is a gap in research with regard to an empirically substantiated classification scheme for subtypes of hate speech for the German law enforcement and reporting center domain. Based on a review of relevant computer science publications (N=24) and qualitative interviews with practitioners (N=18), this work investigates practice-relevant subtypes of hate speech and finds that it is primarily differentiated with regard to targeted group affiliations, the conveyance of an immediate security threat, and criminal relevance. It contributes to the state of research with an empirically grounded online hate speech classification scheme for German law enforcement agencies and reporting centers (C1) and five implications for the user-centered design of hate speech classification tools (C2).enhttp://purl.org/eprint/accessRights/RestrictedAccessText/Workshop Paper10.18420/muc2024-mci-ws13-124