Sentic Web: A New Paradigm for Managing Social Media Affective Information

Abstract

The recent success of media-sharing services caused an exponential growth of community-contributed multimedia data on the Web and hence a consistent shift of the flow of information from traditional communication channels to social media ones. Retrieving relevant information from this kind of data is getting more and more difficult, not only for their volume, but also for the different nature and formats of their contents. In this work, we introduce Sentic Web, a new paradigm for the management of social media affective information, which exploits AI and Semantic Web techniques to extract, encode, and represent opinions and sentiments over the Web. In particular, the computational layer consists in an intelligent engine for the inference of emotions from text, the representation layer is developed on the base of specific domain ontologies, and the application layer is based on the faceted browsing paradigm to make contents available as an interconnected knowledge base.