On the Effectiveness and Optimization of Information Retrieval for Cross Media Content

In recent years, the growth of Social Network communities has posed new challenges for content providers and distributors. Digital contents and their rich multilingual metadata sets need improved solutions for an efficient content management. There is an increasing need of services for scaling digital services, searching and indexing. Despite the huge amount of contents, users want to easily find relevant unstructured documents in large repositories, on the basis of multilingual queries, with a limited waiting time. At the same time, digital archives have to be fully accessible even if a major restructuring is in progress, or without a significant downtime. Evaluating the effectivness of retrieval systems plays a fundamental role in the process of system assessment and optimization. This paper presents an indexing and searching solution for cross media content, developed for a Social Network in the domain of Performing Arts. The research aims to cope with the complexity of a heterogeneous indexing semantic model, with tuning techniques for discrimination of relevant metadata terms. Effectiveness and optimization analysis of the retrieval solution are presented with relevant metrics. The research is conducted in the context of the ECLAP project (http://www.eclap.eu).