Indexing and Navigation within a Video based on Content Analysis of Microblogs

This paper underlines the relevance and usefulness of indexing multimedia segments thanks to associated microblog posts, for various multimedia applications, such as in-media social navigation, multimedia summarization or composition, or exploration of multimedia collections according to various socially-based viewpoints. Our main contribution is a framework, to index and retrieve socialized multimedia segments (i.e. video and associated social interactions) according to several perspectives derived from text mining techniques and topic modeling. In addition, we report and discuss a user experiment validating the fundamental assumption of using social interactions to index videos.