NLTP Content Meetings – September 16 – Dimensions of Semantic Change: Applying the SIBling Framework to Mental Health Concepts by Naomi Baes

We’re pleased to welcome Naomi Baes from the University of Melbourne to our NLTP Content Meeting on September 16, where they will give a talk on Dimensions of Semantic Change: Applying the SIBling Framework to Mental Health Concepts. The meeting link is available on request. See details below.

Title: Dimensions of Semantic Change: Applying the SIBling Framework to Mental Health Concepts

Abstract: Lexical semantic change takes many forms, yet existing approaches often examine them in isolation. I present SIBling, a three-dimensional framework for modelling semantic change through shifts in (1) Sentiment (the valence of a word’s contexts), (2) Intensity (emotional arousal or the use of intensifiers), and (3) Breadth (the diversity of contexts in which a word appears). Together, these dimensions provide an integrated and computationally efficient way of mapping how the meanings of concepts evolve over time. I illustrate the framework with case studies of mental health related concepts, showing how they have broadened, intensified, or shifted in sentiment across decades of text. These results illuminate cultural trends such as pathologization, stigma, and concept creep, demonstrating how the SIBling toolkit captures capture socially significant conceptual change.

Main publications the presentation is based on:

1. Naomi Baes, Nick Haslam, and Ekaterina Vylomova. 2024. A Multidimensional Framework for Evaluating Lexical Semantic Change with Social Science Applications. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1390–1415, Bangkok, Thailand. Association for Computational Linguistics.
2. Naomi Baes, Raphael Merx, Nick Haslam, Ekaterina Vylomova, and Haim Dubossarsky. 2025. LSC-Eval: A General Framework to Evaluate Methods for Assessing Dimensions of Lexical Semantic Change Using LLM-Generated Synthetic Data. In Findings of the Association for Computational Linguistics: ACL 2025, pages 10905–10939, Vienna, Austria. Association for Computational Linguistics.