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.
Riccardo Fusaroli
📚 Reading Women in Cognitive Science 📚
“Recommendations for readings are welcome, especially in the history of cognitive science (prior to 1950s, and the older the better).”
irisvanrooijcogsci.com/2026/02/15/%...
The authors launch a campaign to collect "parkinson voices" at a large scale, across countries. Ted talks, lots of outreach. The data starts flocking in. 4/
Occasionally, I make threads on social media about papers and books that I read. It helps me focus and process deeper when I share highlights and thoughts with others. In this blogpost, I compile a…
We've never been able to find a validated person-reported measure of conversational success. So our team created one. Developed and validated with help from over 900 participants. Can be used in both research and clinical settings. Check it out!
rdcu.be/fnFs0 @healthandstats.bsky.social
The data is collected during clinical visits, ensuring the task is correctly performed in soundproof booths, with high quality mics, relying on clear cases of parkinson's, w good diagnostics and checks. The performance of the algorithm is quite solid. So.... 3/
prepping a talk I am re-reading one of my favorite cases of neurological vocal markers, often used as an argument for psychiatric vocal markers: unstead prolonged phonation in parkinson. Short thread 1/
Speech is both complicated and complex. Neuropsychiatric conditions the same. We should think a bit more carefully about the constructs we target, before letting stats/ml/"ai" go vrrrrrrrrooooom :-)
Another good explainer on our recent registered report by @murillopagnotta.bsky.social
Even in presence of a clear mechanistic link, accuracy drops to clinical uselessness, even w improved algorithms. Recording contexts and equipments change, patients and controls are less clear and more complex cases, more variation in task performance... 5/
A. Tsanas showed quite persuasively that having a good mechanistic model of how motor control degeneration impact voice production can lead to v high accuracy in assessing parkinson severity from prolonged phonations (say aaaaaaaaaaaaa) 2/
