Geo-word centric association rule mining Katsumi Takahashi, Iko Pramudiono, and Masaru Kitsuregawa   View Paper (PDF)   Return to Session 10. Mobile applications Abstract Association rule mining is a well known data mining technique that also applicable to spatial data. Here we systematically elaborate spatial association rule mining which focusing on the "geo-word" in order to analyze location related preferences of human users. We propose several categories of mining methodologies based on the items in the rule and rule generation process. Novel interestingness metrics are derived out of those mining methodologies to identify location specific characteristics such as local specialties and common words. An experiment on real access logs from a commercial yellowpage site is conducted to examine the effectiveness of those methodologies ©2006 Association for Computing Machinery