I am a tenured Assistant Professor with the Web Information Systems group, at the Delft University of Technology. I am Research Fellow at the AMS Amsterdam Institute for Advanced Metropolitan Solutions, where I coordinate the research activities in the Data Science Enabling Technologies work line. I am faculty fellow with the IBM Benelux Center of Advanced Studies.
I hold a Ph.D. in Computer Science, obtained at Politecnico di Milano with a thesis focused on model driven approaches for the design, development and automatic code generation of Search Based Applications.
My research lies at the intersection of human computation, user modeling, and web information retrieval. I study and build novel Social Data Science methods and tools. My goal is to help improving well-being and fostering inclusion by means of Web-based, personalized social computing systems that combine the cognitive and reasoning abilities of individuals and crowds, with the computational powers of machines, and the value of big amounts of heterogeneous data.
I published more than 100 publications in peer-reviewed international journals (TWEB, IEEE Internet Computing, Semantic Web Journal, VLDB Journal), conferences (WWW, HCOMP, RecSys, AAAI, IJCAI, CIKM, UMAP, HyperText, ICWE, ISWC, SIGIR), and workshops. I am co-author of the book “Web Information Retrieval” (Springer, 2013). I am co-inventor of the US patent "Method and system of management of queries for crowd searching" (US 8825701 B2, 2015).
My work is driven by societal and business needs, and finds natural applications and valorization in a variety of contexts. I am principal investigator of the Social Glass project (Intelligent Cities); and principal investigator at the AMS Amsterdam Institute for Advanced Metropolitan Solutions, working on data science enabling technologies. I currently hold a Faculty Fellow position at the IBM Benelux CAS, where I am principal investigator of the Inclusive Enterprise line of research (Enterprise Workforce Engagement).
Previously, I have been actively involved in the definition and execution of several Italian, Dutch, and European research projects addressing: urban data fusion, multi--platform, reactive, social-network based crowdsourcing; multi-domain Web search; human-enhanced audiovisual search; and other projects related to Web technologies, and Web architectures for embedded systems.
These are the great colleagues that are currently part of my research team. Together, we strive to create the next generation of crowd-powered Web-based system, while advancing the state-of-the-art, and creating societal and econimical impact.
Despite targeted policies and technological innovations, household energy consumption is still increasing in Europe. This project seeks to break this impasse by enabling behavioral change through the design, implementation and assessment of learning feedback loops supported by a web-based platform. It will enhance individual and community learning processes and inform policies for the smart use of big data.
CODA Loop is transdisciplinary and experimental, aiming at: a) understanding data-driven learning feedback loops between individuals and communities to enable behavioral change in energy choices, b) generating ‘Individual to Community’ and ‘Community to Policy’ loops through designing and testing a learning support software for data-sharing, c) analyzing and assessing the interaction among individuals and groups within this platform to inform wider policies for energy transitions. The project delivers: a) a prototype learning platform for sharing data about individual and community energy consumption choices; b) a plan for the marketization and wider application of this platform: c) policy recommendations for enabling learning and behavioral change towards reduced energy use. CODALoop combines cutting edge cognitive modeling, data analysis and qualitative research methods.
More information about CODA Loop is available on http://jpi-urbaneurope.eu/codaloop/
My Role: leader of WP5 - Design of social data collection, integration, analysis and sense making (for data- driven learning and adaptation feedback loops). CODA Loop is an ERA-NET Cofund Smart Cities and Communities project. It includes 13 partners with diverse backgrounds and focuses on a set of selected urban areas through a living lab approach.
Social Glass is a novel web-based platform that supports the analysis, valorisation, integration, and visualisation of large-scale and heterogeneous urban data in the domains of city planning and decision-making.
The platform systematically combines publicly available social datasets from municipalities together with social media streams (e.g. Twitter, Instagram and Foursquare) and resources from knowledge repositories. It further enables the map- ping of demographic information, human movement pat- terns, place popularity, traffic conditions, as well as citizens’ and visitors’ opinions and preferences with regard to specific venues in the city.
Social Glass has been applied in several real-world case studies, which demonstrated the framework’s conceptual properties, and its potential value as a solution for urban analytics and city-scale event monitoring and assessment.
More information, videos and demos about Social Glass are available on www.social-glass.org
My Role: principal investigator. Social Glass is a research partially funded by the EIT ICT Labs, and by the Amsterdam Institute for Advanced Metropolitan Solutions.
For companies across the globe, building and sustaining a talent pipeline has become top priority.
Several studies show that extrinsic factors, such as salary and payment, are not the core reason for employee retention. On the other hand job satisfaction, the ”degree to which individuals like their jobs”, is key; it depends on variables such as structure, size, pay, working conditions and leadership, which represent the organisational climate.
We believe that an happy employee is a productive employee and less likely to leave, and we advocate inclusion, “a sense of belonging: feeling respected, valued for who you are; feeling a level of supportive energy and commitment from others so than you can do your best work”, as a core property of next generation enterprises. To achieve this vision, we take a computer science angle, by asking ourselves the question: how can computer systems help to foster inclusion and well-being in the enterprise?
My Role: principal investigator. This research line is conducted in collaboration with IBM Benelux, and its Center of Advanced Studies.
Finding relevant multimedia content is notoriously difficult, and the difficulty increases with the size and heterogeneity of the content collection. Linked cultural media collections are heterogeneous by nature and rapidly increase in size, mainly through enormous amounts of user-generated content and metadata that are placed on the Internet on a daily basis. Without mechanisms for keeping any part of these collections easily accessible by any user at any time and any use context, the value of these collections for the community will drop, just like their value as an economic asset.
In close collaboration with the Rijksmuseum Amsterdam, we aim at understanding which strategies and techniques lead to high-quality annotations by (crowds of) users that are external to the museum. The first challenge of the project is to identify the niche of relevant experts and to motivate them to contribute to the annotation of artworks. As a next step, the personalization mechanisms must make sure that the experts are shown items that correspond to their expertise. The quality of the annotations and annotators are to be evaluated using trust algorithms. Finally, all these aspects must be presented in an appropriate interface.
To evaluate our hypotheses, we develop a framework designed to support crowd annotation processes, called Accurator.
My Role: Leader of the Worktable 2, addressing the Rijksmuseum Amsterdam Use Case. Responsible for the “Web user demand elicitation (WUDE)” work package. Coordinator of the demonstration and implementation activities.
SEALINCMedia is a research funded by COMMIT/ initative.
The research team from TU Delft and DAT.Mobility worked on intelligently fusing data about pedestrian flows from different types of sensors (wifi, gps, counting cameras) to estimate crowd densities, travel speeds and flows at different routes of SAIL. Besides that, open social media platforms were crawled and analysed to get insight in demographics of the crowd and crowd sentiments at different hotspots of SAIL during the event. The collected data and state estimates can be used for more advanced and efficient crowd management support in the future. At SAIL 2015 we really focused on testing new sensor technologies, crowd data algorithms and analytics and assess whether they can be made useful and are reliable. This should give us insight in how we can improve crowd management of large events in cities in the future and provide visitors and citizens a more pleasurable experience.
My Role: Coordinator of the research activities related to social media data.
More information about the SAIL 2015 crowdmanagement project is available on AMS Institute
City Data Fusion is a project, funded by the ICT Labs of the European Institute of Innovation and Technologies (EIT), which aims at enhancing the ability to feel the pulse of our cities to deliver innovative services. To this end, this research is collecting in real-time data streams of different types ranging from social networks (e.g., Twitter and Foursquare) to sensor networks (e.g., Traffic Flow Sensing and Mobile Phone Data). Crowdsourcing techniques, tailored to incentives applicable in urban environment and to urban life styles, are under investigation to cleanse and enrich those data streams. Last but not least, innovative technologies, methodologies and systems for data fusion, analysis and visualization are researched to magnify their value.
My Role: TU Delft project leader; coordinator of the research activities of the project.
More information, videos and demos about City Data Fusion are available on http://citydatafusion.org
City Data Fusion is funded by EIT ICT LABS,URBAN LIFE AND MOBILITY.
CrowdSearcher is a crowd-management system that implements a paradigm that embodies crowds and social network communities as first-class sources for the information management and extraction on the Web.
Retrieval and management of Web data is becoming a more and more complex problem, due to the amount of information to be dealt with, to the diversity of the information sources and of the data formats, and to the evolving expectations of users. More and more users are increasingly relying on social interaction to complete and validate the results of their online activities.
For instance, scouting "interesting" results, or suggesting new, unexpected search directions in information seeking processes, occurs in most times aside of the search systems and processes, possibly instrumented and mediated by a social network. Moreover, tasks such as quality assessment, opinion making, and sense extraction cannot be completely delegated to automatic procedures.
The CrowdSearcher approach aims at filling the gap between traditional Web systems (CMS, search engines and others), which operate upon world-wide information, with social systems, capable of interacting with real people, in real time, to capture their opinions, suggestions, and emotions by leveraging crowdsourcing practices and making them viable upon a social network. Thanks to the proposed approach, the data management and manipulation experience of users can be enormously enriched.
My Role: designer; architect; coordinator of the research, implementation and release activities of the project. Co-inventor of patent US8825701 B2 "Method and system of management of queries for crowd searching"
More information, videos and demos about Social Glass are available on http://crowdsearcher.search-computing.org/
CrowdSearcher is part of the Search Computing (Seco) project funded by the European Research Council (ERC) "IDEAS Advanced Grants".
Search Computing (SeCo) is a multi-disciplinary science which will provide the abstractions, foundations, methods, and tools required to answer these and many similar questions.
Search Computing focuses on building the answers to complex search queries by interacting with a constellation of cooperating search services, using ranking and joining of results as the dominant factors for service composition.
My Role: responsible for the “Human-Computer interfaces for Multi-domain Search”, “CrowdSearching”, and “SPARQL-Rank” research tracks; responsible for the demonstration activities of the project; designer of the Search Computing architecture; and coordinator of the implementation and release activities.
Search Computing (SeCo) is a project submitted to the "IDEAS Advanced Grants" and selected for funding by the European Research Council (ERC). The starting date of the project is November 1st, 2008.
The CUbRIK project aimed at introducing real innovative patterns inside the Multimedia search domain, proposing the paradigm of human-enhanced time-aware multimedia search. CUbRIK's goal was to enhance the quality of search experience by augmenting the precision and the relevance of results when machine intelligence fails or is unable to remove uncertainty. The approach is not to emulate, but rather to incorporate human and social capabilities from feature extraction to search and validation of multimedia content: because we, the humans, still have a lot to teach machines about semantic understanding of multimedia content!
The CUbRIK Consortium consisted of 15 partners, including research centers, universities and companies.
The CUbRIK project started in October 2011.
My Role: responsible for the “Social and Human Interaction” activities of WP3; responsible for the CUbRIK platform modeling, and contributor to several project deliverables. I left the project in January 2013, before moving to TU Delft.
CUbRIK was a 8.9M, 36 month Collaborative Project, partially funded by the European Commission's in FP7, Grant agreement no: 287704. More information about CUbRIK is avaialble at www.cubrikproject.eu
PHAROS (Platform for searcHing of Audiovisual Resources across Online Spaces) was an Integrated Project co-financed by the European Union under the Information Society Technologies Programme (6th Framework Programme) – Strategic Objective ‘Search Engines for Audiovisual Content’ (2.6.3). The PHAROS mission was to advance audiovisual search from a point-solution search engine paradigm to an integrated search platform paradigm. The platform has been built on an innovative, open, and distributed architecture that aimed at enabling consumers, businesses and organisations to unlock the values found in audiovisual content.
My Role: responsible for the work-packages related to the platform modeling and the demonstration activities of the project. Main author of the deliverables related to platform demonstra- tions; responsible for the coordination of the implementation and integration activities of several platform modules. Organizer and lecturer at the PHAROS Summer School.
More information about is avaialble at www.pharos-audiovisual-search.eu/