BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.com//sips2025-budapest//speaker//3GYJQX
BEGIN:VTIMEZONE
TZID:CET
BEGIN:STANDARD
DTSTART:20001029T040000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10
TZNAME:CET
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20000326T030000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3
TZNAME:CEST
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:pretalx-sips2025-budapest-T3TXAV@pretalx.com
DTSTART;TZID=CET:20250626T094000
DTEND;TZID=CET:20250626T095000
DESCRIPTION:This lightning talk will pitch how large language models (LLMs)
  can serve as intellectual partners in the classification of psychological
  phenomena in text (“psychological text classification”). Drawing on e
 mpirical work (Bunt et al.\, in press) where we developed and tested the v
 alidity of LLM-driven classifiers for phenomena such as reported speech an
 d conversational repairs\, I will argue that prompt-based interactions wit
 h LLMs can quickly generate insights on how to refine conceptualisations a
 nd operationalisations in the realm of text classification. Rather than re
 placing human coders\, LLMs act as “collaborators” in an iterative cyc
 le of classification and feedback\, helping researchers spot ambiguities i
 n definitions\, catch errors\, and challenge assumptions. This synergy can
  strengthen validity in psychological measurement\, enabling both more rob
 ust conceptualisation of psychological phenomena in text and the efficient
  scaling of text-based research. By embracing LLMs as intellectual partner
 s\, we can advance methodological rigour and improve psychological science
 .
DTSTAMP:20260514T155739Z
LOCATION:Second floor 214
SUMMARY:LT24: LLMs as intellectual partners: strengthening validity in psyc
 hological text classification - Hannah Bunt
URL:https://pretalx.com/sips2025-budapest/talk/T3TXAV/
END:VEVENT
END:VCALENDAR