Department of Computer, Control and Management Engineering

Studying information propagation in social media is an important task with plenty of applications for business and science. Generating realistic synthetic information cascades can help the research community in developing new methods and applications, testing sociological hypotheses and different what-if scenarios by simply changing few parameters. We demonstrate WoMG, a synthetic data generator which combines topic modeling and a topic-aware propagation model to create realistic information-rich cascades, whose shape depends on many factors, including the topic of the item and its virality, the homophily of the social network, the interests of its users and their social influence.