2015 3rd International Conference on Future Internet of Things and Cloud (FiCloud) (2015)
Aug. 24, 2015 to Aug. 26, 2015
This paper describes an approach to detect automatically events in real-time by analyzing big data streams coming from a social network. The described event detection algorithm is a burst-based event detection methods extended by a dynamically adapted reference corpus. The usage of adaptive reference corpora produces much accurate results compared with static reference corpora.
Event detection, Twitter, Time-frequency analysis, Real-time systems, Heuristic algorithms, Algorithm design and analysis
J. Nutzel and F. Zimmermann, "Improved Burst Based Real-Time Event Detection Using Adaptive Reference Corpora," 2015 3rd International Conference on Future Internet of Things and Cloud (FiCloud)(FICLOUD), Rome, Italy, 2015, pp. 512-518.