Honored to host Prof. Marta González at our KDD Lab in Pisa! Her talk on the Science of Cities at Scuola Normale Superiore (@sns.it) was deeply inspiring.
A true privilege to meet the researcher who sparked my passion for human mobility. #UrbanScience #Mobility #Cities
📢 New paper! We study urban location recommenders and their feedback with human mobility. Simulating this loop reveals a paradox: people explore more individually, yet city visits and encounters concentrate. Cities coevolve with AI, and inequality can grow.
📄 link.springer.com/article/10.1...
The first episode of our gentrification saga is finally open access!
www.worldscientific.com/doi/10.1142/...
@nicopedre.bsky.social @lucapappalardo.bsky.social
This #OpenAccess study from 'Machine Learning' represents the first attempt to study how the human-AI feedback loop reshapes human mobility patterns. bit.ly/4c64FvV @gmauro10.bsky.social @lucapappalardo.bsky.social #AI #ML
Three lightning talks by KDD Lab of Pisa at @css-conference.bsky.social in Siena, in a few minutes in the plenary room!
Delighted to share that my group at CNR won a FIS Consolidator grant (the “Italian ERC”) to study City-AI Coevolution.
We’ll investigate how the human-AI feedback loop shapes human mobility and urban life.
🚦 How diverse are your city’s routes?
Today at @ic2s2.bsky.social (lightning talks), @gcornacchia.bsky.social presents: “Route Diversification in Road Networks”.
We introduce DiverCity, a metric to quantify how traffic can spread across alternative routes.
#HumanMobility #Routing #ic2s2
Giovanni Mauro
Luca Pappalardo
In Boston for @netsciconf.bsky.social. See you on Friday 11:15 for session PS 3.6 Mobility, Spatial & Urban Networks 3
The urban impact of algorithmic navigation
D. Pedreschi
lnkd.in/dAG-v4PF
The urban impact of AI: modelling feedback loops in location-based recsys
L. Pappalardo
lnkd.in/dR4JjCCQ
How do recommender systems shape our behavior?
📄 We review 144 studies across domains, from social media to GenAI.
🧭 With the EU Digital Services Act, data access is now possible. Our survey offers a guide to studying recommender-driven risks.
🔗 arxiv.org/abs/2407.01630
ACS is an international, peer-reviewed journal, uniquely publishing in multidisciplinary approaches, either empirical or theoretical, to the study of complex systems.
