Title :
A review of retrospective news event detection
Author :
Ramadan, Qusai Hussein ; Mohd, Masnizah
Author_Institution :
Knowledge Technol. Res. Group, Univ. Kebangsaan Malaysia, Bangi, Malaysia
Abstract :
Retrospective news event detection (RED) has been studied for many years in order to discover previous unidentified events. There are ongoing works done to improve RED techniques such as distance measure and clustering approaches to overcome issues such as huge dimensionality of data. This paper discusses three major sequential stages in RED (data preprocessing, data representation and data organization) and reports the limitation in each stage. Finally we present the suggested RED with respect to crimes domain.
Keywords :
data handling; data structures; information resources; pattern clustering; police data processing; RED; data dimensionality; data organization; data preprocessing; data representation; distance clustering; distance measure; retrospective news event detection; Accuracy; Clustering algorithms; Data mining; Data preprocessing; Event detection; Measurement; Organizations; Retrospective news event detection; crime;
Conference_Titel :
Semantic Technology and Information Retrieval (STAIR), 2011 International Conference on
Conference_Location :
Putrajaya
Print_ISBN :
978-1-61284-354-4
Electronic_ISBN :
978-1-61284-353-7
DOI :
10.1109/STAIR.2011.5995790
