Negativity and semantic change

Speaker: Will Hamilton (Stanford University, USA)

Date: 17 August 2017

Time: 15:00 – 16:00

Venue: The Alan Turing Institute.

Watch event video


It is often argued that natural language is biased towards negative differentiation, meaning that there is more lexical diversity in negative affectual language, compared to positive language. However, we lack an understanding of the diachronic linguistic mechanisms associated with negative differentiation. In this talk, I will review key concepts related to negative differentiation and discuss how I am using dynamic word embeddings to test whether negative lexical items are more semantically unstable than positive ones. Preliminary results suggest that rates of semantic change are faster for negative affectual language, compared to positive language. I will finish my talk by discussing some practical consequences of this positive/negative asymmetry for modern sentiment analysis tools.

Biography

Will Hamilton is a Ph.D. Candidate at Stanford University and works jointly with professors Dan Jurafsky (NLP Group) and Jure Leskovec (Network Analysis Group). His work focuses on developing machine learning methods with large-scale social science applications. He is currently supported by the SAP Stanford Graduate Fellowship and an Alexander Graham Bell Canada Graduate Scholarship. Before joining Stanford, Will was an MSc student in the Reasoning and Learning Lab at McGill University, under the supervision of Joelle Pineau.