Project homepage

Crowds and Machines for Modeling and Discovering Controversy

ControCurator aims to enable for modern information access systems to discover and understand controversial topics and events by bringing together different types of crowds (niches of experts, lay crowds and engaged social media contributors) and machines in a joint active learning workflow for the creation of adequate training data both realtime and offline.

In ControCurator the tools and algorithms will be validated in new domains with different niches of experts (media studies scholars and professionals from the media industry), and with different types of media (social media, videos and video transcripts/subtitles) and will be also combined with complementary paid crowdsourcing and machine processing of text.

People Involved