A Knowledge-Based System For The Dynamic Generation And Classification Of Novel Contents In Multimedia Broadcasting

In this work we exploit a recently introduced nonmonotonic extension of Description Logics, able to deal with the problem of knowledge invention via commonsense concept combination, to dynamically generate novel editorial contents in the context of a real broadcasting company: RAI - Radiotelevisione Italiana, the Italian public broadcaster. In particular, we introduce the system implementing such logic, i.e. DENOTER: Dynamic gEnerator of NOvel contents in mulTimEdia bRoadcasting (available online at the URL: http://di.unito.it/denoter), that has been applied and tested in the online multimedia platform of RAI (i.e. RaiPlay) as a tool for both the generation/suggestion of novel genres of multimedia on-demand contents and the reclassification of the available items within such new genres. Our system works by extracting the typical properties characterizing the available genres (with a standard information extraction pipeline) and by building novel classes of genres as the result of a creative combination of such extracted representations. We have tested DENOTER (i) by reclassifying the available contents in RaiPlay with respect to the new generated genres (ii) with an evaluation, in the form of a controlled user study experiment, of the feasibility of using the obtained reclassifications as recommended contents (iii) with a qualitative evaluation done with a small group of experts of RAI. The obtained results are encouraging and pave the way to many possible further improvements and research directions.