Socially motivated multimedia topic timeline summarization

As the amount of social media shared on the Internet grows increasingly, it becomes possible to explore a topic with a novel, people based viewpoint. Contrasting with traditional man-made topic summarization which provide the personal view of its author, we want to focus on public reaction to events. To this end, we propose an approach to automatically generate a timeline of popular events related to a given topic. Time segments of interest are extracted from Google Trends results using a simple statistical approach. Each event, relevant to the specified topic, is illustrated on a timeline by videos mined from social media sharing platforms that gives context to the events and offers an overview of what has caught people's attention. We report the results provided by our approach for automatically illustrating the popular moments of four celebrities.