(Partial) User Preference Similarity as Classification-Based Model Similarity
Amancio Bouza and Abraham Bernstein

swj251_1.pdf 1.69MB
Type: Paper
Tags:

Bibtex:
@article{,
title = {(Partial) User Preference Similarity as Classification-Based Model Similarity},
journal = {Semantic Web – Interoperability, Usability, Applicability},
author = {Amancio Bouza and Abraham Bernstein},
year = {2012},
url = {http://www.semantic-web-journal.net/content/partial-user-preference-similarity-classification-based-model-similarity},
license = {},
abstract = {Recommender systems play an important role in helping people finding items they like. One type of recommender system is collaborative filtering that considers feedback of like-minded people. The fundamental assumption of collaborative filtering is that people who previously shared similar preferences behave similarly later on. This paper introduces several novel, classification-based similarity metrics that are used to compare user preferences. Furthermore, the concept of partial preference similarity based on a machine learning model is presented. For evaluation the cold-start behavior of the presented classification-based similarity metrics is evaluated in a large-scale experiment. It is shown that classification-based similarity metrics with machine learning significantly outperforms other similarity approaches in different cold-start situations under different degrees of data-sparseness.}
}

Send Feedback Start
   0.000003
DB Connect
   0.000459
Lookup hash in DB
   0.001289
Get torrent details
   0.000426
Get torrent details, finished
   0.000870
Get authors
   0.000003
Select authors
   0.000578
Parse bibtex
   0.000162
Write header
   0.000605
get stars
   0.000403
home tab
   0.000414
render right panel
   0.000008
render ads
   0.000038
fetch current hosters
   0.000762
Done