BEGIN:VCALENDAR VERSION:2.0 PRODID:-//events.la.psu.edu//EN CALSCALE:GREGORIAN BEGIN:VTIMEZONE TZID:America/New_York BEGIN:STANDARD DTSTART:20201101T020000 TZOFFSETFROM:-0400 TZOFFSETTO:-0500 RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU END:STANDARD BEGIN:DAYLIGHT DTSTART:20200308T020000 TZOFFSETFROM:-0500 TZOFFSETTO:-0400 RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU END:DAYLIGHT END:VTIMEZONE BEGIN:VEVENT UID:16891-583573b1afa6e776d318794567821841@events.la.psu.edu DTSTAMP:20260412T053330Z DTSTART;TZID=America/New_York:20201016T090000 DTEND;TZID=America/New_York:20201016T103000 SUMMARY:Roger Beaty (Penn State) - Using Computational Semantic Models to Assess Verbal Creativity DESCRIPTION:Using Computational Semantic Models to Assess Verbal Creativ ity\n\nConducting creativity research often involves asking several huma n raters to judge responses to verbal creativity tasks. Although such su bjective scoring methods have proved useful\, they have two inherent lim itations—labor cost (raters typically code thousands of responses) and s ubjectivity (raters vary on their perceptions of creativity)—raising cla ssic psychometric threats to reliability and validity. In this talk\, I attempt to address these limitations by capitalizing on recent developme nts in automated scoring of verbal creativity via semantic distance\, a computational method that uses natural language processing to quantify t he semantic relatedness of texts. Five studies compared the top performi ng semantic models (e.g.\, GloVe\, continuous bag of words) previously s hown to have the highest correspondence to human relatedness judgements. We assessed these semantic models in relation to human creativity ratin gs from a canonical verbal creativity task and novelty/creativity rating s from two word association tasks. We find that a latent semantic distan ce factor—comprised of the common variance from five semantic models—rel iably predicts human ratings across all creativity tasks\, with semantic distance explaining over 80% of the variance in creativity and novelty ratings. We also replicate an established experimental effect in the cre ativity literature and show that semantic distance correlates with other creativity measures\, demonstrating convergent validity. I conclude by describing an open platform that can efficiently compute semantic distan ce\, and I discuss potential applications of semantic distance for asses sing creative language use.\n\nFor more details: https://events.la.psu.e du/event/roger-beaty-penn-state-using-computational-semantic-models-to-a ssess-verbal-creativity/ X-ALT-DESC;FMTTYPE=text/html:

Using Computational Semantic Models to Assess Verbal Crea tivity

Conducting creativity research often involves asking sever al human raters to judge responses to verbal creativity tasks. Although such subjective scoring methods have proved useful, they have two inhere nt limitations—labor cost (raters typically code thousands of responses) and subjectivity (raters vary on their perceptions of creativity)—raisi ng classic psychometric threats to reliability and validity. In this tal k, I attempt to address these limitations by capitalizing on recent deve lopments in automated scoring of verbal creativity via semantic distance , a computational method that uses natural language processing to quanti fy the semantic relatedness of texts. Five studies compared the top perf orming semantic models (e.g., GloVe, continuous bag of words) previously shown to have the highest correspondence to human relatedness judgement s. We assessed these semantic models in relation to human creativity rat ings from a canonical verbal creativity task and novelty/creativity rati ngs from two word association tasks. We find that a latent semantic dist ance factor—comprised of the common variance from five semantic models—r eliably predicts human ratings across all creativity tasks, with semanti c distance explaining over 80% of the variance in creativity and novelty ratings. We also replicate an established experimental effect in the cr eativity literature and show that semantic distance correlates with othe r creativity measures, demonstrating convergent validity. I conclude by describing an open platform that can efficiently compute semantic distan ce, and I discuss potential applications of semantic distance for assess ing creative language use.

For more details: https://events.la.psu.edu/event/rog er-beaty-penn-state-using-computational-semantic-models-to-assess-verbal -creativity/

END:VEVENT END:VCALENDAR