Threshold-Calibrated Word Sense Disambiguation: Semantic Broadening Without Sense Redistribution in Schizophrenia
Presented work with Nick Haslam introducing a threshold-calibrated, prototype-based pipeline for tracking word sense prevalence in historical corpora. Applied to 109,940 uses of schizophrenia in U.S. news media, the study shows that rising semantic change scores can reflect contextual diversification within a stable dominant sense rather than sense redistribution, sense loss, or polysemization.
Mar 28, 2026
A Multidimensional Framework for Evaluating Lexical Semantic Change with Social Science Applications
Presented the foundational SIBling paper at ACL 2024. The paper introduces a multidimensional framework for modeling lexical semantic change across Sentiment, Intensity, and Breadth, and applies it to semantic shifts in mental health and mental illness.
Aug 14, 2024