ABSTRACT
The emergence of the Web, wireless technologies, and mobile devices has made the automated extraction of knowledge from dynamic user context based on mobile device usage an important research area. However, the interpretation of extracted knowledge to provide personalized services requires machine learning (ML) techniques to facilitate higher system reasoning accuracy. The semantic web is challenged with numerous issues, including ontology availability, content availability; the scalability of semantic web content; development and evolution; multilingualism; visualization; and integration of noisy heterogeneous data. Knowledge of social functions of mobile device users can be represented to aid the deployment of personalized services through the use knowledge graph (KG) and ontology modeling. The constructed KG can find diverse applications, including location-based services, events, agents, and artificial intelligence (AI)-enabled assistance to analysts. This work uses semantic web technologies such as KG and ontology to develop a framework for automatic reasoning of extracted contextual information from mobile devices for knowledge sharing. A recreational facility KG is developed to support tourists receiving personalized recommendations about centers that provide recreational services with geographic locations to boost their health and well-being. This service deployment indicates that KG and ML integration can improve automatic reasoning, ontology enrichment, context-aware services, data interpretation, and the accuracy of recommendation systems for multilingual visualization.
