New in PNAS! 📢 lnkd.in/d7z2VEjh 👉 We show how combining individual & collective behavior boosts out-of-routine mobility prediction 👉 We found collective behavior strongly impacts individual mobility in dense urban areas. 👉 The model is robust to severe behavioral changes (e.g., COVID pandemic)

𝗧𝗵𝗲 𝗟𝗟𝗠 𝗪𝗲𝗮𝗿𝘀 𝗣𝗿𝗮𝗱𝗮: 𝗔𝗻𝗮𝗹𝘆𝘀𝗶𝗻𝗴 𝗚𝗲𝗻𝗱𝗲𝗿 𝗕𝗶𝗮𝘀 𝗮𝗻𝗱 𝗦𝘁𝗲𝗿𝗲𝗼𝘁𝘆𝗽𝗲𝘀 𝘁𝗵𝗿𝗼𝘂𝗴𝗵 𝗢𝗻𝗹𝗶𝗻𝗲 𝗦𝗵𝗼𝗽𝗽𝗶𝗻𝗴 𝗗𝗮𝘁𝗮 🛍️ arxiv.org/html/2504.01... What is your gender if you purchased tech gadgets? What if you bought a cooking pan? LLMs can guess gender with moderate accuracy but they often rely on biases and stereotypes 😬

🚀 New on arXiv "Towards Civic Digital Twins: Co-Designing the Citizen-Centric Future of Bologna" arxiv.org/abs/2412.06328 🛠️ Co-design & citizen engagement are key to future urban development. We explored the vision, challenges, & opportunities for Civic Digital Twins.

Eventually, my first post on BSKY 😄 Thanks for having me @mattiamazzoli.bsky.social and @isi.it!

Mattia Mazzoli@mattiamazzoli.bsky.social · 2y ago

@maxluca.bsky.social giving a seminar at @isi.it on the advantages and limitations of LLMs in predicting human mobility in urban spaces

What an incredible experience at the European Mobility Symposium! Huge thanks to @ric-dicle.bsky.social for co-organizing and to all the participants for the enriching discussions. See you at the next edition! #EMoS #HumanMobility