BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Modelling the language of extremist communities - Christine de Koc
 k\, University of Melbourne
DTSTART:20250808T130000Z
DTEND:20250808T140000Z
UID:TALK234880@talks.cam.ac.uk
CONTACT:Anna Talas
DESCRIPTION:Extremist groups develop complex in-group language\, also refe
 rred to as cryptolects\, to exclude or mislead outsiders. Though this is a
  longstanding and well-documented social norm\, it highlights key shortcom
 ings in current natural language processing technologies\, e.g. large lang
 uage models (LLMs)\, especially when used for content moderation. In this 
 talk\, I will describe recent methods\, datasets\, and models we developed
  to address these challenges. Our experiments center on two online extremi
 st platforms\, Incels and Stormfront\, which promote alt-right and misogyn
 istic ideologies\, respectively.\n\nZoom link: https://cam-ac-uk.zoom.us/j
 /83115049986?pwd=6W5bzFb49HcCbWqz6HR3tRhpVxubTb.1
LOCATION:Webinar &amp\; FW11\, Computer Laboratory\, William Gates Buildin
 g.
END:VEVENT
END:VCALENDAR