jogl

Integrating Behavior, Text, and Networks to Forecast Online Participation

| Marc Santolini

As online platforms increasingly rely on voluntary contributions—from open science to collaborative innovation—the ability to anticipate user engagement becomes both a scientific and practical priority. Yet predicting who will stay active, who will disengage, and why, remains a complex challenge. Our recent paper, KEGNN: Knowledge-Enhanced Graph Neural Networks for User Engagement Prediction (Fan et al., International Conference on Multimedia Retrieval 2025), introduces a novel framework that addresses this gap by integrating behavioral, social, and semantic signals into a unified predictive model.

Continue reading →

Community Review Systems in Science Funding

| Marc Santolini

Resource allocation is crucial for the development of innovative projects in science and technology. In response to the urgent COVID-19 pandemic in 2020, we implemented an agile “community review” system with JOGL to quickly allocate micro-grants for the prototyping of innovative solutions. In this paper published in f1000Research we analyzed the results of 7 review cycles. Implemented across 147 projects, this process is characterized by its speed (median duration of 10 days), scalability (4 reviewers per project regardless of the total number of projects), and robustness, measured by the preservation of the projects’ ranking order after the random removal of reviewers. Including applicants in the review process does not introduce significant bias, showing a correlation of r=0.28 between evaluations, similar to that observed for non-applicants and within traditional funding methods. This system allows for agile improvement of proposals, promoting the implementation of successful early prototypes and the constructive revision of initially rejected projects. This work demonstrates the effectiveness of a frugal community review for agile resource allocation in open innovation contexts.

The Architecture of Collective Intelligence: What We Learned from Covid-19

| Marc Santolini

Can a global crisis awaken new forms of collective intelligence?

In the early days of the Covid-19 pandemic, I wrote an article for The Conversation reflecting on the unprecedented surge of collaborative research and open innovation initiatives emerging worldwide. In particular, I shared the experience of building the OpenCovid19 Initiative on the JOGL platform, where thousands of contributors—from data scientists to high school students—came together to co-develop open-source solutions, from diagnostics to ventilator designs.

This piece explores how digital platforms and participatory methodologies can support large-scale, decentralized collaboration—and asks whether this surge of collective intelligence can be sustained beyond the crisis.

You can read the full article here:
📰 Covid-19: The Rise of a Global Collective Intelligence?

Skill network of Covid-19 projects on the JOGL platform

Our first hackathon with JOGL

| Marc Santolini

With Just One Giant Lab we just organized our first hackathon on Open Data and Vaccination for our first program Co-Immune! We had 6 teams with great ideas and projects using data science to better understand vaccination hesitancy and access to vaccines. More below: