Ed FlahavanUsing Large Language Models to unlock value in unstructured text dataCrime reports, patient records, public consultations, customer complaints. Public services produce enormous volumes of unstructured text…Jan 21Jan 21
Ed FlahavanCan AI Accurately Simulate Cross National Cultural Values? An ExplorationThere’s lots of interest in using large language models (LLMs) to augment or even replace human participants in research studies.Aug 11, 2023Aug 11, 2023
Ed FlahavaninBehavioural InsightsDiagnosing Opinions: Using AI to simulate focus groups on Junior Doctor strikesIn a recent blog I used AI to create pen portraits of UK voters and then generate survey responses about whether or not they supported the…Apr 27, 2023Apr 27, 2023
Ed FlahavaninBehavioural InsightsThe AI of the beholder: Simulated opinion polling of public attitudes to strikesIn a recent blog I explored whether AI simulations of people completing cognitive tasks could replicate human data. Tl;dr: it can.Apr 16, 2023Apr 16, 2023
Ed FlahavaninBehavioural InsightsJust noise? Using GPT3 to analyse Google reviews of London police stationsAt a push, most of us might leave a review of a particularly good or bad restaurant. But who reviews a police station? And can we learn…Jan 17, 20231Jan 17, 20231