BEGIN:VCALENDAR
PRODID:-//Columba Systems Ltd//NONSGML CPNG/SpringViewer/ICal Output/3.3-
 M3//EN
VERSION:2.0
CALSCALE:GREGORIAN
METHOD:PUBLISH
BEGIN:VEVENT
DTSTAMP:20241101T173428Z
DTSTART:20241126T140000Z
DTEND:20241126T153000Z
SUMMARY:Social Statistics Seminar Series
UID:{http://www.columbasystems.com/customers/uom/gpp/eventid/}a145-m2yz25
 o6-misgnd
DESCRIPTION:Friedrich Geiecke\nAssistant Professor of Computational Socia
 l Science\, London School of Economics \n\nConversations at Scale: Robus
 t AI-led Interviews with a Simple Open-Source Platform (joint with Xavie
 r Jaravel)\n\nThe advent of large language models (LLMs) provides an opp
 ortunity to conduct qualitative interviews at a large scale\, with thous
 ands of respondents\, creating a bridge between qualitative and quantita
 tive methods. In this paper\, we develop a simple\, versatile open-sourc
 e platform for researchers to run AI-led qualitative interviews. Our app
 roach incorporates established best practices from the sociology literat
 ure\, uses only a single LLM agent with low latency\, and can be adapted
  to new interview topics almost instantaneously. We assess its robustnes
 s by drawing comparisons to human experts and using several respondents-
 based quality metrics. Its versatility is illustrated through four broad
  classes of applications: eliciting key factors in decision making\, pol
 itical views\, views of the external world\, and subjective mental state
 s. High performance ratings are obtained in all of these domains. The pl
 atform is easy to use and deploy: we provide detailed explanations and c
 ode for researchers to swiftly set up and test their own AI-led intervie
 ws.\n
STATUS:TENTATIVE
TRANSP:TRANSPARENT
CLASS:PUBLIC
LOCATION:Arthur Lewis_2.016/2017 Boardroom
END:VEVENT
END:VCALENDAR