LivingKnowledge: A Platform and Testbed for Fact and Opinion Extraction from Multimodal Data

In this paper, we describe the work we are undertaking in producing a truly multimedia platform for the analysis of facts and opinions on the web. The system integrates the analysis of multimodal data (images, text and page layout) into a distributable platform that can be built upon for various applications. We give an overview of the natural language processing tools that have been developed for extracting facts and opinions from the textual content of articles, the image analysis techniques used to extract facts and to help support the opinions found in the contextually related written information, as well as other multimodal tools developed for the analysis of online articles. We describe two applications that have been developed as part of ongoing work of the Living Knowledge project: the News Media Analysis application for the semi-automation of the work of a media analysis company and the Future Predictor application which allows exploration of claims that are made through time.