Mining events connections on the social web: Real-time instance matching and data analysis in EventMedia

摘要

Event and media services have recently witnessed a rapid growth driving the way people explore information of interest. A significant amount of social calendars, media memes and background knowledge are daily created on various platforms, conveying event clues or past users experience. Mining, in real-time, the connection of these distributed data fragments provides a key advantage not only to deliver enriched views, but also to gain insight into interesting sociological aspects. To this aim, we harness the power of Semantic Web technologies as means to easily steer the data integration and analysis. Our overall goal is to build a web-based environment that allows users to discover meaningful, surprising or entertaining connections between events, media and people. In this paper, we present EventMedia, a platform that provides descriptions of events associated with media, and interlinked with the Linked Data cloud. It draws on a live data update and a real-time interlinking to face the natural dynamics of events. A user-friendly interface has been designed to meet the user needs: relive experiences based on media and support decision making for attending upcoming events.