TY - GEN
T1 - Detecting bursty events in collaborative tagging systems
AU - Yao, Junjie
AU - Cui, Bin
AU - Huang, Yuxin
AU - Zhou, Yanhong
PY - 2010
Y1 - 2010
N2 - Collaborative tagging systems have emerged as an ubiquitous way to annotate and organize online resources. The users' tagging actions over time reflect the changing of their interests. In this paper, we propose to detect bursty tagging event, which captures the relations among a group of correlated tags where the tags are either bursty or associated with bursty tag co-occurrence. We exploit the sliding time intervals to extract bursty features from large tag corpora as the first step, and then adopt graph clustering techniques to group bursty features into meaningful bursty events. An experimental study demonstrates the superiority of our approach.
AB - Collaborative tagging systems have emerged as an ubiquitous way to annotate and organize online resources. The users' tagging actions over time reflect the changing of their interests. In this paper, we propose to detect bursty tagging event, which captures the relations among a group of correlated tags where the tags are either bursty or associated with bursty tag co-occurrence. We exploit the sliding time intervals to extract bursty features from large tag corpora as the first step, and then adopt graph clustering techniques to group bursty features into meaningful bursty events. An experimental study demonstrates the superiority of our approach.
UR - https://www.scopus.com/pages/publications/77952759151
U2 - 10.1109/ICDE.2010.5447922
DO - 10.1109/ICDE.2010.5447922
M3 - 会议稿件
AN - SCOPUS:77952759151
SN - 9781424454440
T3 - Proceedings - International Conference on Data Engineering
SP - 780
EP - 783
BT - 26th IEEE International Conference on Data Engineering, ICDE 2010 - Conference Proceedings
T2 - 26th IEEE International Conference on Data Engineering, ICDE 2010
Y2 - 1 March 2010 through 6 March 2010
ER -