Overview of Event-based Collective Knowledge Management in Multimedia Digital Ecosystems
The paper provides an overview on the problem of event-based collective knowledge management from shared multimedia data. We start by introducing key concepts and constructs related to the problem, including multimedia digital ecosystems, collaborative environments, and collective knowledge management. Then, we utilize a real world motivating scenario to highlight some of the major challenges facing event-based knowledge organization in a multimedia collaborative environment, mainly the need to handle: i) heterogeneous data sources and their unstructured content, ii) large and growing volumes of data published online, iii) non-consistent and ambiguous multimedia data annotations, iv) misleading contents (that are not event related) published by non-experienced users, and vi) multimedia data with missing event-related meta-data. Consequently, we provide a short review of existing methods related to event detection from shared social multimedia data on the Web, contrasting their characteristics with respect to the above challenges, before highlighting potential research directions (including the use of data normalization, semantic mediation, and semantic disambiguation to resolve discrepancies, and promoting inter-connectivity between intelligent agents).