Media Technology MSc

Finding News in a Haystack


We present NewsClu, an approach to collect, cluster, categorize and select news articles from the Internet. The framework is not limited to a certain field, resort or division of news – it is capable to work on any topic and runs on real time live data on the Internet. NewsClu keeps its user informed about that particular topic by filtering, organizing, ranking and clustering of news according to static, dynamic and social factors. Through event based clustering the framework filters duplicate and less relevant news, making it easier to read more interesting news in less time. NewsClu is innovative in terms of clustering and ranking compared to other approaches.


Martin Weber and Maarten H. Lamers, Finding News in a Haystack — Event Based News Clustering with Social Media Based Ranking. In: Proceedings of the 2013 IEEE Third International Conference on Cloud and Green Computing (CGC), pp 321-326, 2013