Correlating Time-Related Data Sources with Co-clustering

TitleCorrelating Time-Related Data Sources with Co-clustering
Publication TypeConference Paper
Year of Publication2008
AuthorsKoutsonikola, Vassiliki A., Sophia G. Petridou, Athena Vakali, Hakim Hacid, and Boualem Benatallah
EditorBailey, James, David Maier, Klaus-Dieter Schewe, Bernhard Thalheim, and Xiaoyang Sean Wang
Book TitleWISE
ISBN Number978-3-540-85480-7

A huge amount of data is circulated and collected every dayon a regular time basis. Given a pair of such datasets, it might be possibleto reveal hidden dependencies between them since the presence of the onedataset elements may influence the elements of the other dataset and viceversa. Furthermore, the impact of these relations may last during a periodinstead of the time point of their co-occurrence. Mining such relationsunder those assumptions is a challenging problem. In this paper, we studytwo time-related datasets whose elements are bilaterally affected overtime. We employ a co-clustering approach to identify groups of similarelements on the basis of two distinct criteria: the direction and durationof their impact. The proposed approach is evaluated using time-relatednews and stock’s market real datasets.


auth logo

Location & Contact

Department of Informatics
Aristotle University of Thessaloniki
Thessaloniki GR-54124

t  | (+30) 2310 998415
e |