Five new NERDS publications out!

We have been very productive this year already! Five new NERDS publications are released this week:

  1. Which sport is becoming more predictable? A cross-discipline analysis of predictability in team sports, by M. Coscia, published in EPJ Data Science

    We analyze more than 300,000 professional sports matches in the 1996-2023 period from nine disciplines, to identify which disciplines are getting more/less predictable over time. We investigate the home advantage effect, since it can affect outcome predictability and it has been impacted by the COVID-19 pandemic. Going beyond previous work, we estimate which sport management model – between the egalitarian one popular in North America and the rich-get-richer used in Europe – leads to more uncertain outcomes. Our results show that there is no generalized trend in predictability across sport disciplines, that home advantage has been decreasing independently from the pandemic, and that sports managed with the egalitarian North American approach tend to be less predictable. We base our result on a predictive model that ranks team by analyzing the directed network of who-beats-whom, where the most central teams in the network are expected to be the best performing ones.

  2. Algorithmic Fairness: Learnings From a Case That Used AI For Decision Support, by V. Sekara, T.S. Skadegard Thorsen, and R. Sinatra, published by the Crown Princess Mary Center

    This policy brief provides a small introduction to algorithmic fairness and an example of auditing fairness in an algorithm which was aimed at identifying and assessing children at risk from abuse.

  3. The Parrot Dilemma: Human-Labeled vs. LLM-augmented Data in Classification Tasks, by A.G. Møller, J.A. Dalsgaard, A. Pera, L.M. Aiello (accepted at EACL’24).
    How good are Large Language Models in generating synthetic examples for training classifiers? To find out, we used GPT4 and Llama2 to augment existing training sets for typical Computational Social Science tasks. Our experiments show that the time to replace human-generated training data with LLMs has yet to come: human-generated text and labels provide more valuable information during training for most tasks. However, artificial data augmentation can add value when encountering extremely rare classes in multi-class scenarios, as finding new examples in real-world data can be challenging. 

  4. Shifting Climates: Climate Change Communication from YouTube to TikTok, by A. Pera, L.M. Aiello (accepted at WebSci’24).

    How do video content creators tailor their communication strategies in the era of short-form content? We conducted a comparative study of the YouTube and TikTok video productions of 21 prominent climate communicators active on both platforms. We found that when using TikTok, creators use a more emotionally resonant, self-referential, and action-oriented language compared to YouTube. Also, the response of the public aligns more closely to the tone of the videos in TikTok.

  5. The role of interface design on prompt-mediated creativity in Generative AI, by M. Torricelli, M. Martino, A. Baronchelli, L.M. Aiello (accepted at WebSci’24).
    We analyze 145k+ user prompts from two Generative AI platforms for image generation to see how people explore new concepts over time, and how their exploration might be influenced by different design choices in human-computer interfaces to Generative AI. We find that creativity in prompts declines when the interface provides generation shortcuts that deviate the user attention from prompting.

NERDS back from D3A conference

Last week several of us NERDS took part in the first D3A conference in Nyborg, where an astonishing 500 data scientists from all around Denmark met to discuss the latest research in the field.

The Danish Digitalization, Data Science and AI (D3A) is a new national conference hosted by Pioneer Centre for AI (P1), Danish Data Science Academy (DDSA), and Digital Research Center Denmark (DIREC). 

While most of us just enjoyed the company and the scientific inspirations in a perfectly organized setting, two of us also presented actively: Sandro presented a poster on science & gender, while Ane co-organized the workshop “An interdisciplinary dive into Climate IT”, presenting our research on bicycle networks.

Here a few visual impressions from our trip:

We hope to see you in future editions of the conference, the next one coming up in October.

Michael Szell wins EU Horizon grant

As one of 32 partners, Michael Szell / ITU is part of the EU (Horizon) project

JUST STREETS – Mobility justice for all: framing safer, healthier and happier streets

that has just started! The consortium includes 12 European cities representing more than 4.5 million citizens. The project aims to transform cities’ car-centered mobility narratives that take for granted that streets are for motorized traffic only, to promote walking, cycling and other active modes of mobility.

To reach this goal, ITU’s part of the project will develop algorithmic methods to study low traffic neighborhoods and bicycle/pedestrian networks, and analyze mobility data with focus on safety, for better planning of human-centric, sustainable mobility.

This grant will provide us funding for a new PhD student, Clément Sebastiao, who has recently joined our group.

PhD Open Call 2024

The ITU-wide PhD Open Call 2024, deadline Feb 25th, is now open!  If your research overlaps with ours and you are interested, get in touch!

Either reach out directly to one of us, or use the student contact form on our students page, where you can also get inspiration for potential research projects. All professors at NERDS are open to PhD supervision and have good ideas for possible PhD projects, so don’t hesitate to reach out. One of our PhD students, Anastassia, has joined us previously through this call.

In Denmark, PhD students are employees, where both salary and working conditions are excellent. The NERDS group is a down-to-earth and fun place to be. Copenhagen is often named as the best city in the world to live in, and for good reasons. It’s world-renowned for food, beer, art, music, architecture, the Scandinavian “hygge”, and much more. In Denmark, parental leave is generous, and child-care is excellent and cheap.

Clément Sebastiao has joined NERDS

Happy new year! 🥳

We are thrilled to welcome Clément Sebastiao to our research group!

Clément joins us as PhD student for 3 years, funded by a EU project we cannot yet legally talk about (but soon), supported by his new supervisor Michael Szell. He completed his Master’s degree in 2023 from ENS Lyon in Complex Systems and Physics. He also has ample experience with internships, including at our friends at ISI Foundation and also at NERDS in 2022, where he started a project on bicycle network growth. He will continue in this vein, developing algorithmic methods to study bicycle/pedestrian networks, low traffic neighborhoods, and mobility data with focus on safety, for better planning of sustainable mobility. Given his interdisciplinary background and know-how in complex networks and systems, he is the ideal candidate for this task, ensuring a smooth takeover of the bicycle network / urban data science torch passed by our now last-year PhD students Ane and Anastassia.

New NERDS papers: Network reorganization, Mastodon migration, News sharing on Facebook

We have three brand new papers out, this time in PNAS, Scientific Reports, and the Journal of Quantitative Description:

  1. Socioeconomic reorganization of communication and mobility networks in response to external shocks, by L. Napoli, V. Sekara, M. García-Herranz, and M. Karsai, published in PNAS

    We analyze mobile phone communication data to investigate the dynamics of network segregation patterns of the same set of people both in terms of mobility and of social communication during the initial wave of COVID-19 in Sierra Leone. Interestingly, we find opposite trends in the network segregation dynamics, characterized overall by simultaneous increase in mobility segregation and reduction in social network segregation. Our results underscore the significance of data-driven studies going beyond single-axis approaches to assess the impact of emergency policies.
  2. Drivers of social influence in the Twitter migration to Mastodon, by L. La Cava, L.M. Aiello, and A. Tagarelli , published in Scientific Reports

    We analyzed the social network and the public conversations of about 75,000 users who migrated from Twitter to Mastodon, as we NERDS did too a year ago, and observed that the temporal trace of their migrations is compatible with a phenomenon of social influence, as described by a compartmental epidemic model of information diffusion. Drawing from prior research on behavioral change, we delved into the factors that account for variations of the effectiveness of the influence process across different Twitter communities.
    Read more in our blog post:
    https://communities.springernature.com/posts/get-out-of-the-nest-drivers-of-social-influence-in-the-twitter-migration-to-mastodon
  3. Cracking Open the European Newsfeed, by L. Rossi, F. Giglioetto, and G. Marino, published in Journal of Quantitative Description: Digital Media

    This paper contributes to the ongoing effort to describe and quantify the quality of information that is shared on large social media platforms. We do this by complementing existing research that provided a first quantitative assessment of the quality of the information circulating on Facebook among US users. Leveraging an updated version of the same data source — Meta’s URL Shares Dataset — and replicating much of the methodology, we quantify the trustworthy and untrustworthy links to external websites that have been shared on Facebook in the period between 2019 and 2022 in three major European countries (Germany, France, and Italy). We observe a clear decline in the number of URLs present in the dataset and an increase in the URLs from untrustworthy domains as a percentage of the total URLs shared in a year. This increase seems to be higher in electoral years (in Germany and in Italy) but it does not translate into an increase of Views received from untrustworthy sources.

NERDS calls for papers: Social good, Sustainable mobility, Spatial data science

NERDS are currently involved in co-organizing special issues for societally relevant research.

Here our three open calls for papers:

  1. Complex Systems for Social Good
    Advances in Complex Systems, NERDS co-organizer: Vedran Sekara
    CFP, deadline Dec 15th: https://www.worldscientific.com/page/acs/callforpapers01
    Data, data science, machine learning, and AI tools and evidence are becoming increasingly important to tackle the complex challenges of climate change, social inequalities, geopolitical crises, migration, and public health emergencies. Complex Systems can provide a robust theoretical framework to address critical operational issues for vulnerable contexts such as replicability and transferability of results, explainability of models, and understanding of the challenges of algorithmic systems and possible biases. This topical issue has the goal of reviewing the potential contributions that Complex Systems can have on creating public value and producing public policy practices.
  2. Spatial Data Science for Planning
    GeoForum Perspektiv, NERDS co-organizer: Ane Rahbek Vierø
    CFP (expression of interest), deadline Jan 15th: https://journals.aau.dk/index.php/gfp/announcement/view/207
    We invite submissions that align with the themes of Spatial Data Science, encompassing for example Python, R, AI/ML, Business Intelligence, and their integration with geographic data. Authors are encouraged to explore both theoretical and practical aspects, sharing insights, case studies, methodologies, and real-world applications. Accepting both English and Danish contributions.
  3. Urban Mobility and Green Transportation in Sustainable Cities 
    Journal of Physics: Complexity, NERDS co-organizer: Michael Szell
    CFP, deadline May 31st: https://iopscience.iop.org/collections/jpcomplex-231012-387
    This Focus aims to explore the intersection of physics and complexity in the context of urban mobility and green transportation, shedding light on cutting-edge research that not only elucidates the fundamental principles governing these systems but also offers practical applications to create more sustainable and efficient cities. Regarding the green transportation, it can be any means of travel that does not negatively impact the environment, including (but are not limited to) bikes (dockless or docked sharing ones), ebikes (both private or sharing ones), electric vehicles. A better green transportation would involve both the infrastructure level and human behaviors level.

Please contact us for any questions regarding these calls. Happy writing/submitting!

Roberta wins ERC Consolidator grant!

Wow – Roberta Sinatra just won an ERC Consolidator grant! We congratulate her with all our hearts to this once-in-a-lifetime achievement!

An ERC Consolidator grant comes with 2 million EUR for 5 years and enables “a scientist who wants to consolidate their independence by establishing a research team and continuing to develop a success career in Europe”.

Roberta’s excellence, her interdisciplinarity, and her proposed topic just hit the right nerve:

scAIence: Quantifying AI-infused Science

The goal of scAIence is to quantify whether, how, and with which implications generative AI is changing how scientists write, communicate, and diffuse their science, and to explore rigorously the opportunities, dangers, and implications of scientists augmenting their scientific writing with AI. The focus of scAIence is quantitative and based on large-scale data and controlled experiments, since we lack a systematic analysis of AI-generated science: All our evidence regarding AI-generated writing is anecdotal or based on small case studies.

Within the scAIence project, Roberta and her team will deploy a novel computational social science approach, based on a wide array of quantitative disciplines, leveraging large-scale databases of human-generated information and controlled experiments. scAIence will break new ground by (i) introducing the quantitative methods required to understand AI-infused science, (ii) redefining metrics and models to account for AI-generated content in science, and (iii) delivering quantitative scientific insights into how AI is changing the diffusion of science. Taken together, scAIence will lay the scientific foundation for the quantitative study of AI-infused science.

The scAIence project is planned to take place at Roberta’s main affiliation SODAS at Copenhagen University – follow Roberta for upcoming hiring calls for PhD students and Postdocs.