Aggregate two-way co-clustering of ads and user analysis for online advertisements

Meng Lun Wu, Chia Hui Chang, Rui Zhe Liu, Teng Kai Fan

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Scopus citations


Clustering plays an important role in data mining, as it is used by many applications as a preprocessing step for data analysis. Traditional clustering focuses on grouping similar objects, while two-way co-clustering can group dyadic data (objects as well as their attributes) simultaneously. In this research, we apply two-way co-clustering to the analysis of online advertising where both ads and users need to be clustered. The key data that connect ads and users are contained in the user-ad link matrix, which denotes the ads that a user has linked. We proposed a three-staged clustering that makes use of the three data matrices to enhance clustering performance. In addition, an iterative cross co-clustering algorithm is also proposed for two-way co-clustering. The experiment is performed using the advertisement and user data from Morgenstern, a financial social website that focuses on the agent of advertisements. The result shows that three staged clustering provides better performance than traditional clustering, while iterative co-clustering completes the task more efficiently.

Original languageEnglish
Title of host publicationICS 2010 - International Computer Symposium
Number of pages7
StatePublished - 2010
Event2010 International Computer Symposium, ICS 2010 - Tainan, Taiwan
Duration: 16 Dec 201018 Dec 2010

Publication series

NameICS 2010 - International Computer Symposium


Conference2010 International Computer Symposium, ICS 2010


  • Clustering evaluation
  • Co-clustering
  • Decision tree
  • Dyadic data analysis
  • KL divergence


Dive into the research topics of 'Aggregate two-way co-clustering of ads and user analysis for online advertisements'. Together they form a unique fingerprint.

Cite this