2008 Seventh International Conference on Machine Learning and Applications 2008
DOI: 10.1109/icmla.2008.121
|View full text |Cite
|
Sign up to set email alerts
|

Does Wikipedia Information Help Netflix Predictions?

Abstract: Abstract

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
7
0

Year Published

2010
2010
2023
2023

Publication Types

Select...
4
2
1
1

Relationship

0
8

Authors

Journals

citations
Cited by 14 publications
(7 citation statements)
references
References 6 publications
0
7
0
Order By: Relevance
“…The results are fairly comparable to our approach. The orange curve with diamond markers exploits Wikipedia to feed a content-based recommender system, as proposed in [5]. Finally, the green curve with dash markers refers to a CB recommender system leveraging DBpedia [9].…”
Section: Discussionmentioning
confidence: 99%
See 1 more Smart Citation
“…The results are fairly comparable to our approach. The orange curve with diamond markers exploits Wikipedia to feed a content-based recommender system, as proposed in [5]. Finally, the green curve with dash markers refers to a CB recommender system leveraging DBpedia [9].…”
Section: Discussionmentioning
confidence: 99%
“…They leverage only text information sources, while we exploit structured and disambiguated information contained within RDF triples. In [5] the authors use the text content and the hyperlink structure of Wikipedia pages to identify similarities between movies. The aim is to check whether Wikipedia may improve the results of recommendations.…”
Section: Related Workmentioning
confidence: 99%
“…Web Directory. Wikipedia was used to estimate similarity between movies [20] in order to provide recommendations for the Netflix Prize competition by using a k-nearest neighbor and a pseudo-SVD algorithm. In [47], an approach for filtering RSS feeds and e-mails is presented, which makes use of Wikipedia to automatically generate the user profiles from the user's document collection.…”
Section: Semantic Information For User and Item Representationsmentioning
confidence: 99%
“…Based on certain feature representation methods, the similarity measure between users and videos is the basis for recommendation. Miller et al [15] used the content and hyperlink structure of Wikipedia to define the similarity between two movies and used the knearest neighbor algorithm for movie recommendation. Experiments showed that the knowledge of Wikipedia did not significantly improve the performance of the recommender system.…”
Section: Introductionmentioning
confidence: 99%