Scale up behavioral measurement w ML& you get extra noise & bias. "Classification errors distort findings in automated speech processing," by @lucasgautheron.bsky.social, Kidd, Malko, @marvinlavechin.bsky.social & @acristia.bsky.social shows how to deal w that: pubmed.ncbi.nlm…
Who's Who of AI
Riccardo Fusaroli
Cognitive Science at Aarhus Uni. Curious about social interactions, symbolic behaviors, and meta-science. Focus on stats, computational modeling, machine learning, complex systems, language, exp semiotics and neuropsychiatric conditions. He/They.
What they're sharing
pubmed.ncbi.nlm.nih.gov
Articles & links
Their own posts
Recent commentary
w misgivings, I've been using LLMs to reproduce the manual data extraction from my published meta-analyses. Against my worst temptations (and fears) the pipeline ended up being the opposite of vibe coding. 1/