Tracking and Analyzing TV Content on the Web through Social and Ontological Knowledge


People on the Web talk about television. TV users’ social activities implicitly connect the concepts referred to by videos, news, comments, and posts. The strength of such connections may change as the perception of users on the Web changes over time.

With the goal of leveraging users’ social activities to better understand how TV programs are perceived by the TV public and how the users’ interests evolve in time, MeSoOnTV defines a knowledge graph to model the integration of the heterogeneous and dynamic data coming from different information sources, including broadcasters’ archives, online newspapers, blogs, web encyclopedias, social media platforms, and social networks, which play a role in what we call the ”extended life” of TV content.

For more details, please visit the MeSoOnTV home page.


A context-aware navigation system

CoSeNa screenshot

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 behavior of the CoSeNa System is described in: M. Cataldi, C. Schifanella, K. S. Candan, M. L. Sapino, L. Di Caro. "CoSeNa: a context-based search and navigation system". In MEDES09, International ACM Conference on Management of Emergent Digital EcoSystems, Lyon, 2009.

A demostration version of the software can be downloaded [here].

A metadata-informed co-clustering framework

Metadata-informed co-clustering

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, proposes three different algorithms to metadata-informed coclustering, named metadata-driven, metadata-constrained and metadata-injected.

Details about the proposed techniques can be found in: C. Schifanella, M. L. Sapino, K. S. Candan "On Context-Aware Co-Clustering with Metadata Support". Journal of Intelligent Information Systems, 2011. Springer. To appear.

The software library is developed in Java: to obtain it, please write to Claudio Schifanella.


Condensing navigable tag hierarchies from tag clouds


TMine organizes tags extracted from textual content in hierarchical organizations, suitable for navigation, visualization, classification, and tracking. TMine extracts the most significant tag/terms from text documents and maps them onto a hierarchy in such a way that descendant terms are contextually dependent on their ancestors within the given corpus of documents. This offers a mechanism for enabling navigation within the tag space and for classification of the text documents based on the contextual structure captured by the created hierarchy. Tmine is language neutral, since it does not rely on any natural language processing technique and is unsupervised.

The software library is developed in Java: to obtain it, please contact us.


A pattern development view system for multidimensional scientific data visualization.


pDView, the pattern development view, is a system for multidimensional scientific data visualization. The pDView system relies on a novel pattern development tree (pDTree) structure to unravel patterns in multidimensional data without having to rely on visualizations that require either significant degrees of projections that eliminate certain dimensions at the expense of the others or introduce significant visual overhead due to overly-rich multi-dimensional graphic interfaces. Instead, pDView maps data along all its relevant dimensions onto a pDTree structure, capturing and visualizing the underlying fundamental relationships. The user is able to vary contextual parameters to observe the strength and robustness of these relationships under different situations

The software library is developed in Java: to obtain it, please contact us.


QUery-driven Exploration of Semistructured data and meta-data with conflicTs and partial knowledge

QUEST, the QUery-driven Exploration of Semistructured data and meta-data with conflicTs and partial knowledge, is a system for supporting the integration of scientific data and taxonomies in the presence of misalignments and conflicts. QUEST relies on a novel constraint-based data model that captures both value and structural conflicts and enables researchers to observe and resolve such misalignments in the integrated data by considering the context provided by the data requirements of given research questions.

Valid XHTML 1.0 Strict CSS Valido!