When mining the Social Web (e.g. Twitter) for information then one has to understand the content that people contribute on platforms such as Twitter. In the context of Twitter Incident Management, we investigate technologies for understanding the semantic meaning of social data. For example, we developed the so-called GeniUS framework which exploits Linked Open Data to make the semantic meaning of social data explicit. This semantic enrichment of the data allows applications to better exploit the data and make more reliable decisions.
Given the huge stream of messages that are posted on platforms such as Facebook or Twitter, a core challenge is to separate the valuable signals from the noise. With the Twinder search engine, we investigate scalable solutions to filtering problems on Social Web streams. Twinder combines semantic technologies with traditional data mining and allows for estimating the relevance of Twitter messages with high accuracy. Our research in the context of Twinder focuses on various challenges that are related to information filtering such as top k retrieval, duplicate detection or stream reasoning.
In this project, we investigate solutions that support people in browsing Social Web streams. Faceted search interfaces allow people to explore content along various facets. We develop and study adaptive faceted search on Twitter streams. Powered by semantic enrichment, our faceted search framework provides meaningful facets to the user. Context and user modeling functionality moreover allows for suggesting interesting search facets to the user and thus adapt the browsing experience to the demands of the user.
Bringing the different components of TIM technology together allows for different applications in the public safety domain. For example, TIM technology has been successfully applied already to support emergency services such as the Dutch police forces. The screencast shows an example application that has been used to monitor information during emergency incidents in real-time.
Fabian Abel, Claudia Hauff, Geert-Jan Houben, Richard Stronkman, Ke Tao. Semantics + Filtering + Search = Twitter Incident Management. Exploring Information in Social Web Streams. In Proceedings of International Conference on Hypertext and Social Media (Hypertext), Milwaukee, USA, 2012. ACM. [bibtex]
Fabian Abel, Claudia Hauff, Geert-Jan Houben, Richard Stronkman, Ke Tao. Twitcident: Fighting Fire with Information from Social Web Streams. In Proceedings of International Conference on World Wide Web (WWW), Lyon, France, 2012. ACM. [bibtex]
Teun Terpstra, Arnout de Vries, Geerte Paradies, Richard Stronkman. Towards a realtime Twitter analysis during crises for operational crisis management. In: Proceedings of 9th International Conference on Information Systems for Crisis Response and Management (ISCRAM), Vancouver, Canada, 2012.