Stanford InfoLab Publication Server

Exploiting Hierarchical Domain Structure to Compute Similarity

Ganesan, Prasanna and Garcia-Molina, Hector and Widom, Jennifer (2001) Exploiting Hierarchical Domain Structure to Compute Similarity. Technical Report. Stanford.




The notion of similarity between objects finds use in many contexts, e.g., in search engines, collaborative filtering, and clustering. Objects being compared often are modeled as sets, with their similarity traditionally determined based on set intersection. Intersection-based measures do not accurately capture similarity in certain domains, such as when the data is sparse or when there are known relationships between items within sets. We propose new measures that exploit a hierarchical domain structure in order to produce more intuitive similarity scores. We also extend our similarity measures to provide appropriate results in the presence of multisets (also handled unsatisfactorily by traditional measures), e.g., to correctly compute the similarity between customers who buy several instances of the same product (say milk), or who buy several products in the same category (say dairy products). We also provide an experimental comparison of our measures against traditional similarity measures, and describe an informal user study that evaluated how well our measures match human intuition.

Item Type:Techreport (Technical Report)
Subjects:Computer Science > Data Mining
Computer Science > E-Commerce
Related URLs:Project Homepage
ID Code:498
Deposited By:Import Account
Deposited On:28 Jun 2001 17:00
Last Modified:27 Dec 2008 09:55

Download statistics

Repository Staff Only: item control page