Author Archives: luai

Two new NERDS papers: Bias in LLM populations, recommending routes

We have two new publications out!

  1. Emergent social conventions and collective bias in LLM populations, by Ariel Flint Ashery, Luca Maria Aiello, and Andrea Baronchelli, published in Science Advances. Barplots of estimation of individual LLM bias vs. the collective bias they exhibit when playing the naming game
    We explore the collective behavior of LLMs starting from social conventions, the fundamental building blocks of coordinated societies. We used the naming game, a well-established framework that has been applied for decades to study conventions in humans. We found that LLM populations can spontaneously develop shared conventions through local interactions. These interactions can produce collective biases, invisible at the individual level, raising important considerations for AI alignment. Small committed minorities can trigger tipping points, steering the entire group toward new conventions—a dynamic well known in human societies
  2. The experience of running: Recommending routes using sensory mapping in
    urban environments, by Katrin Hänsel, Luca Maria Aiello, Daniele Quercia, Rossano Schifanella, Krisztian Zsolt Varga, Linus W. Dietz, and Marios Constantinides, published in the International Journal of Human-Computer Studies.Map of London with several pairs of alternative running trajectories (urban routes plotted in red, scenic in blue)
    We set out to build running routes not around distance, but around how people feel: before, during, and after a run. We surveyed 387 runners and found that not everyone wants the same kind of run. Some seek quiet and greenery; others thrive on the buzz of people and traffic. Their preferences often match their personality. Runners who prefer scenic paths (quiet, green, and natural) tended to score higher in neuroticism. Those who preferred urban paths (lively and full of people) were more likely to be extroverted. Then, we built a routing engine. Using millions of geotagged Flickr photos and open London data, we scored streets for beauty, noise, safety, and surface quality. We tested the engine on hundreds of 5-km London loops. Most runners preferred the scenic routes.

NERDS at the D3A Conference

NERDS group made a strong return to the second edition of the D3A conference, held in Nyborg. Our presence across the sessions was extensive, starting from Toine welcoming us in the opening session.

The workshop “Networks, Data, Society, and AI”, organized by Vedran, Lasse, Anders, Anders, and Arianna, sparked inspiring dialogue on AI’s impact on society from diverse perspectives, and brought together an eclectic mix of speakers from industry, academia, and journalism.

Anastassia co-led the workshop “From Classroom to Career: Data Science Degrees and Early Career Opportunities,” which provided valuable guidance for young data scientists navigating the transition from academic studies to professional paths. (We were especially pleased to see Luca as one of the invited speakers here, adding an extra point of view to the session!)

Clément contributed a visually engaging poster on urban bicycle network planning, sparking plenty of conversations about sustainable city design. Mesut shared his latest research on fair recommendations in job markets in the “Fair Division – Economics, Computational Social Science, and AI” session.

All in all, this year’s D3A conference was a fantastic blend of intellectual exchange, practical workshops, and community building. It’s exciting to see the role NERDS is playing in these developments, and we’re already looking forward to bringing even more insights to next year’s event!

NERDS at ASONAM’24

A bunch of nerds posing in front of the asonam conference logoLuigi Arminio wins the asonam best phd dissertation award

NERDS’ summer sheneanigans continue at ASONAM, in the beautiful and sunny Calabria. Lucio La Cava and Alessia Galdeman held a tutorial on Mining, Modeling, and Analyzing Decentralized Social Media. Alessia Antelmi organized the HyperSci workshop on Theory and Applications of Hypernetwork Science. Luigi Arminio and Daniele De Vinco presented at the PhD Forum. Luca Aiello fulfilled his duties as the conference Program Chair. Luigi won the prize for the best PhD forum contribution!

NERDS at IC2S2’24 in Philly!

A tactical squad of 6 NERDS attended this year’s IC2S2 in Philly, and presented 9 works:

We are grateful to the organizers for the great event, and we look forward to IC2S2 coming back to scandinavia in 2025!

New NERDS paper on urban morphology & street network simplification

A new NERDS co-authored paper is out open-access in the Journal of Spatial Information Science (JOSIS): A shape-based heuristic for the detection of urban block artifacts in street networks, by Martin Fleischmann & Anastassia Vybornova.

a) Bridge, Amsterdam; b) Roundabout, Abidjan; c) Intersection, Kabul; d) Motorway, Vienna. Polygons classified as face artifacts are shown in red, and the OSM street network (without service roads) is shown in black. Face artifacts are polygons enclosed by street network geometries (in the case of OSM, lane centerlines) that do not represent morphological urban blocks, but instead are a result of detailed transportation-focused mapping of the streetscape. Map data (c) OpenStreetMap contributors (c) CARTO

a) Bridge, Amsterdam; b) Roundabout, Abidjan; c) Intersection, Kabul; d) Motorway, Vienna. Polygons classified as face artifacts are shown in red, and the OSM street network (without service roads) is shown in black. Face artifacts are polygons enclosed by street network geometries (in the case of OSM, lane centerlines) that do not represent morphological urban blocks, but instead are a result of detailed transportation-focused mapping of the streetscape. Map data (c) OpenStreetMap contributors (c) CARTO

We propose a cheap computational heuristic for the identification of ‘face artifacts’, i.e., geometries that are enclosed by transportation edges but do not represent urban blocks. Sounds cryptic? Just check out the picture – the artifacts (in red) might be painfully familiar to anyone who has worked with street network data. Our proposed heuristic, implemented open-source in momepy, is the first step towards a fully automated street network simplification workflow. Next steps coming up – stay tuned!

NERDS at ICWSM’24

This week, Arianna and Anders are representing NERDS at ICWSM in Buffalo, NY, with two freshly-published papers.

  1. Narratives of Collective Action in YouTube’s Discourse on Veganism, by A. Pera and L.M. Aiello. ICWSM’24.

    We studied vegan narratives on YouTube through the lens of a theoretical framework of moral narratitves. We studied how different narratives elicit different types of responses from video commenters, and found that videos advocating social activism are the most effective at stirring reactions marked by heightened linguistic markers that relate to collective action.
  2. The Persuasive Power of Large Language Models by A.G. Møller and L.M. Aiello. ICWSM’24.

    Can artificial agents interact with each other to reproduce human-like persuasive dialogue? And do the arguments they generate sound persuasive to humans? We used Llama2 to test different persuasion strategies, and asked humans to rate them. We found that arguments that included factual knowledge, markers of trust, expressions of support, and conveyed status were deemed most effective according to both humans and agents.

NERDS at Como Summer School and WebSci’24

Arianna and Anders participated to the first editions of the Computational Social Science Summer School in Como, presenting their work on the COCOONS project. Arianna, Daniele, and external collaborator Maddalena Torricelli also attended the WebSci conference in Stuttgard, presenting an analysis of climate action communication on TikTok [paper], the use of hypergraphs to model opinion dynamics in large-scale social media [poster], and the role of interfaces in shaping human creativity during the interaction with generative AI tools [paper].

Welcome Anders to NERDS!

Anders Giovanni Møller graduation at ITU

NERDS welcomes a new member: Anders Giovanni Møller. Starting today, Anders will be a PhD student working with Luca Aiello on the COCOONS project at the intersection between NLP and complex systems. Anders can boast a long tenure at ITU, and last week he got his Master’s degree in Data Science. He was selected for a keynote address to the whole 2023 cohort of ITU MSc graduates during the graduation ceremony — a very moving and inspiring speech! Welcome, Anders!