Great to drop into MLAI's eSafety Hackathon on tackling online harms with AI.

Shout-out to unimelb.bsky.social partner @christinenlp.bsky.social for her work on online extremism (christinedekock.com) and to Macken Murphy's engaging talks on the manosphere (tiktok.com/@mackenmurphy).

Honored to give a talk at the National Research Council Canada on Dimensions of Semantic Change, thanks to Dr Saif Mohammad (NRC-VAD mastermind).

Shared 2 frameworks - SIBling (Sentiment, Intensity, Breadth) + LSC-Eval - applied to mental health concepts.

Slides: www.slideshare.net/slideshow/di...

Had an intellectually stimulating time at the Language models And RePresentations (LARP) 2025 conference, exploring ideas around neuro-symbolic AI and enjoying excellent keynotes from Moa Johansson, Dan Roth, and Vaishak Belle.

See proceedings here: gu-clasp.github.io/LARP/program...

Presenting SIBling at @ic2s2.bsky.social was super enjoyable. Thanks to everyone who dropped by and for the thoughtful discussions!

We successfully presented our findings @aclmeeting.bsky.social Thanks to everyone who stopped by for the thoughtful questions and great discussion!

Excited to present LSC-Eval @aclmeeting.bsky.social! 🎉

This general-purpose framework evaluates methods for assessing dimensions of lexical semantic change using LLM-generated synthetic data to test how well measures detect changes.

📍MON @ 6 pm, Hall 4/5

Paper: aclanthology.org/2025.finding...

SIBling: a framework built for computational social scientists to track semantic shifts on three axes—Sentiment, Intensity & Breadth. We map the conceptual change of “mental health” & “mental illness” and validate SIB measures with LLM-generated data.

📍 Poster 46 @ic2s2.bsky.social • 22 July