Measuring Human Value Expression in Social Media Texts: Calibrated LLM Annotation and Encoder Transfer
Researchers have developed a method to measure human values expressed in social media texts using LLMs. The study, which utilized non-English posts and Schwartz's theory of basic human values, found that different LLMs interpret values differently. Through iterative prompt calibration and error analysis, the accuracy of LLM annotations was improved, and these annotations were then transferred to an encoder model for scalable prediction. AI
IMPACT This research offers a novel approach to analyzing subjective content in social media, potentially improving sentiment analysis and understanding of public opinion.