Adaptive Ontologies for Multimedia Maps
2022
The paper illustrates a web-based framework linking geographic elements with geo and temporal-referenced multimedia contents.Among the key features, -multimedia content integration, time management and self-adaptivity to different application contexts are the most relevant ones.A hybrid approach to classify stored contents combines a Machine Learning (ML) technique for text classification with the intervention of human experts.A dynamically configured ontology-based navigation is proposed based on the adaptivity of the tool to dynamic classification of contents.Adaptive navigation is supported by a general world and by a domain-specific ontology.The approach is presented in a framework and prototype named Multimedia Adaptive Geographic Information System (MAGIS), an extension to Geographic Information Systems (GIS) devised as a common foundation to be adapted to different domainspecific implementations.A demonstration of the web-based MAGIS prototype is provided for Cultural Heritage (CH) events.