Skip to main content
Go to the home page of the European Commission (opens in new window)
English English
CORDIS - EU research results
CORDIS

SoBigData++: European Integrated Infrastructure for Social Mining and Big Data Analytics

Periodic Reporting for period 4 - SoBigData-PlusPlus (SoBigData++: European Integrated Infrastructure for Social Mining and Big Data Analytics)

Reporting period: 2024-01-01 to 2024-12-31

SoBigData++ aimed to establish a distributed, pan-European research infrastructure for big social data analytics while fostering a multidisciplinary research community. Throughout the SoBigData++ project, the research infrastructure has substantially enhanced its services and infrastructure to serve its diverse user community better. One key improvement is the SoBigData e-infrastructure, which has evolved into a dynamic platform for designing and executing complex social mining processes. The suite of analytical tools the research infrastructure offers during the SoBigData++ project has greatly expanded. The project’s online Catalogue now hosts a wealth of new high-quality datasets, algorithms, and ready-to-use methods contributed by the consortium’s research efforts. The e-infrastructure also improved the computational capabilities within the SoBigData Lab, where researchers can seamlessly tap into cloud resources through SoBigData++, allowing them to run large-scale analyses and complex models. Together, these improvements provide a more powerful, versatile ecosystem for big data research on social challenges. Another significant improvement is the training service, which evolved from a repository of materials to a more integrated and homogenous platform called SoBigData Academy, which was designed and implemented by a joint effort between a learning designer and SoBigData researchers, resulting in high-quality courses for the final user. The development of those services always included a strict collaboration with SoBigData Ethical and Legal experts to include the EU Ethical, Legal, Social, Economic, and Cultural (ELSEC) values, as well as following the FAIR (Findable, Accessible, Interoperable, and Reusable) and FACT (Fair, Accurate, Confidential, and Transparent) principles.

The platform is now designed to be accessible even to domain experts outside of computer science (e.g. social scientists, economists, health researchers, and others who may not be data scientists) so they can leverage advanced big data techniques in their work. This inclusive approach has fostered a vibrant community where scientists from various fields, policymakers in public institutions, and industry stakeholders can collaborate and innovate on the platform, providing a common ground and shared resources. In doing so, the project has advanced the state of big data research in Europe, establishing itself as a resource that drives scientific excellence and collaborative innovation.
The main results obtained by the SoBigData++ project can be summarized as follows:
- The project entered the ESFRI Roadmap 2021 during the RP1, and it worked to the end at several activities to ensure the sustainability of the RI in the long term.
- As part of the strategy for developing the SoBigData RI, the consortium agreed to become more effective in increasing its impact at the national level. Following this strategy, the Italian node applied to the Italian RRNP (Recovery and Resilience National Plan) calls for empowering RIs. It won with a project called: “SoBigData.it: Strengthening the Italian RI for Social Mining and Big Data Analytics”.
- Several dissemination and training events have been organized to guarantee a good balance between the quality and impact of the event.
- New datasets, methods, and experiments are integrated into the RI Catalogue from the consortium scientific production, making SoBigData RI a vector for high-quality research, resulting in publications in top conferences and journals.
- A strong collaboration with Horizon Results Booster resulted in a deep understanding and definition of the Key Exploitable Results and Services.

The SoBigData++ project enabled the RI to make a massive step towards defining short- and long-term strategies and defining a realistic path to fulfill the project objectives and beyond. The RI now counts a community of over 13K users subscribed to the different services. During the project, the consortium organized more than 70 events, and our catalogue includes more than 500 datasets, methods and applications.
The impacts of the project are the following:

- ADVANCING THE SOCIAL MINING PLATFORM: SoBigData++ expanded platform functionalities: i) all current services are made available through cloud web-based services and/or high-performance computing software packages; ii) the release of an easy-to-use common interface to design and execute complex social mining experiments relieving the data scientist from being responsible for resource allocation and software installation (based on Python notebook, containerization, etc.) and facilitating the mastering of the complexity of big data analytical processes; iii) The platform is aligned with the EOSC, to become compliant with its policies and be able to utilize computational resources from the European Open Science Cloud.

- EXPANDING THE MULTIDISCIPLINARY COMMUNITY: SoBigData++ extended its community by widening the multidisciplinary communities identified by the current research areas with the contribution of the new partners and a clear plan of actions/events for attracting new users and experiments and returning specialized services to that community.

- OPERATIONALIZING THE ETHICAL AND LEGAL PRINCIPLES: SoBigData++ pursued the EU views on Responsible Research and Innovation will especially uphold values and norms of EU Data Protection law, inspired to strengthen the protection of personal data as a fundamental right, combined with boosting the free flow of personal data as a common good.

- ACCELERATING INNOVATION: SoBigData++ amplified the innovation activities by strengthening the opportunities for cooperation through a privileged communication path for events, projects, hackathons, and boot camps, relying on successful collaboration with industrial and institutional stakeholders (e.g. Challenge Us programme).

- DESIGNING A GOVERNANCE FOR SUSTAINABILITY: SoBigData RI is part of the ESFRI Roadmap 2021 and focuses on becoming an ERIC. SoBigData++ managed membership of all interested entities in Europe – especially those not in the consortium – and posted the basis of the possible governance of the future SoBigData ERIC, which will be the recipient of the RI management at the end of the project.
General Overview of the RI
RI Logo
Project Logo
My booklet 0 0