Claudio Schifanella
Assistant professor
Co-city is winner of the first Urban Innovation Action Call of EU. It is a 5m€ project involving also Città di Torino and ANCI. The topic is supporting the creations of urban commons, using also technologies such as crowdmapping and blockchain. [2016-2019]
Role: scientific responsible of University of Torino’s unit.
More details here
WeGovNow is a European Commission H2020 funded project (4m€) aiming at using state-of-the-art digital technologies in community engagement platforms to engage citizens in decision making processes within their local neighbourhood. Members of the consortium: Università degli Studi di Torino, University College London, Politecnico di Torino, Ruprecht-Karls-Universitat Heidelberg, Città di Torino, Comune di San Donà di Piave, Empirica, Fondazione Giacomo Brodolini, Funka Nu AB, Infalia, London Borough of Southwark, LiquidFeedback, Mapping for Change CIC. [2016-2019]
Role: Task leader of task "Geographical data management" (WP3)
More details here
[2017-2019] NEW! Consortium: CSINIT srl, DOUBLEC sas, WAVE Informatica srl, CSI Piemonte
Librare (“Book on the move”) is an FESR regional project that aimed to transform traditional paper books in virtual objects by tracing their life, uses, readings and movements via sensors applied on the books and connected to mobile applications where users can enter information about collective reading, book-crossing, educational activities, book-related events in the city. [2015-2016]
Consortium: Università degli Studi di Torino, CSP, Trim, Celi Informatica, ULIXE
Role: responsible of the geographical data management module.
More details here
The SEeS@w is an FESR regional project faced workplace safety issues with a socio-technical approach, giving users an active role in risk monitoring and management.[2015-2016]
Consortium: Università degli Studi di Torino, dipartimenti di Informatica, Psicologia, Giurisprudenza, Scienze della Sanità Pubblica e Pediatriche, Sezione Medicina del Lavoro e Scienze Mediche / SUISM. CSP Consoft Sistemi SPA, aGrisù, Augeos, ERPlan, Nomotika, Sicurezza Lavoro.
Role: responsible of the geographical data management module and of the software agent responsible for the integration with the SmartDataNet platform.
More details here
This partnership aims to design and develop a high-level framework for the representation and integration of information from different sources such as traditional media, social networks and web sources. The framework is used for the creation of innovative analysis tools for management of stream of information (both user-generated and editorial) around audio-visual contents. More details at http://hdm.di.unito.it/mesoontv.html
The evaluation of the career of a researcher and its impact on the research community has been deeply studied in literature through the definition of several measures, first among all the h-index and its variations. Although these measures represent valuable tools for analyzing researchers' outputs, they usually assume the co-authorship to be a proportional collaboration between the parts, missing out their relationships and the relative scientific influences. This web application is based on d-index, a novel measure that estimates the dependency degree between authors according to their research environment and along their entire scientific publication history. It proposes a number of visualization tools for analyzing and comparing the careers of all the scientists in the DBLP bibliographic database.
d-index is available at: http://d-index.di.unito.it.
Most of the world's goods are transported in maritime containers, but only a very small amount of them can be physically inspected by customs authorities. The ConTraffic research project of the European Commission aims to demonstrate that an information-based risk analysis system can be successfully used as a first step to select potential illicit containers before costly physical inspections. The ConTraffic system collects container movement data and tries to leverage those heterogeneous, incomplete and sometimes inconsistent information to detect suspicious containers by using novel machine learning and data mining algorithms. We More details at https://ec.europa.eu/jrc/en/scientific-tool/container-traffic-monitoring-system
In traditional co-clustering, the only basis for the clustering task is a given relationship matrix, describing the strengths of the relationships between pairs of elements in the different domains. In many real life applications background knowledge or metadata about one or more of the two input domain dimensions may be available. The proposed framework (developed in Java), proposes three different algorithms to metadata-informed coclustering, named metadata-driven, metadata-constrained and metadata-injected.
The main aim of the project was the development of a television contents recommender based on a novel automatic categorization approach; in fact, the considered categories can evolve in number and meanings depending on the real user context (for example, where the user lives and what happened in her real word). The project considered a very large set of un-structured and semi-structured data (blogs, news web sites, newspapers) as user context, and enriched the existing categories depending on the meanings assumed by them in the most recent contents. Therefore, the categories were organized in structured taxonomies depending on the semantics expressed by the considered domains. These taxonomies have been finally used for indexing the television contents by using novel classification algorithms; using these associations, the system was able to highlight hidden semantic relationships among indexed TV contents, defining the basis for an intelligent television contents recommender.
The CoSeNa System propose an innovative approach to document exploration and retrieval. It allows user to explore text collections leveraging a novel keywords-by-concepts (KbC) graph model, which supports navigation using domain-specific concepts as well as keywords that are characterizing the text corpus. The KbC graph is a weighted graph, created by tightly integrating keywords extracted from documents and concepts obtained from domain taxonomies and supports contextually informed access to these documents.
The main aim of the project is to study how, in a Web 2.0 reality, the most important Italian museum institutions communicate with the potential visitors and how these visitors understand the message vehiculated by them. In order to do that, we analyzed a very large number of contents, related to the considered museums, extracted from the blogosphere (i.e., representing the users point of views) and the official web pages of the examined institutions (i.e. defining the message vehiculated by the museums to their public); thus, we compare these contents by using novel lexical and semantic mechanisms in order to highlight, from a sociological point of view, where and how they significantly differ.
MIUR research project
[2005-2007 – Prof. Alberto Martelli - Università degli Studi di Torino, Università del Piemonte Orientale, Università di Genova, Università di Bologna]
More details here
MIUR research project
[2003-2005 – Prof. Alberto Martelli - Università degli Studi di Torino, Università del Piemonte Orientale, Università di Genova, Università di Bologna]
More details here