TY  - CONF
AU  - Parra, Denis
AU  - Brusilovsky, Peter
A2  - 
T1  - Evaluation of Collaborative Filtering Algorithms for Recommending Articles on CiteULike
T2  - Proceedings of the Workshop on Web 3.0: Merging Semantic Web and Social Web
PB  - 
CY  - 
PY  - 2009/06
M2  - 
VL  - 467
IS  - 
SP  - 
EP  - 
UR  - http://ceur-ws.org/Vol-467/paper5.pdf
M3  - 
KW  - algorithms
KW  - citedBy:doerfel2012leveraging
KW  - collaborative
KW  - filtering
KW  - evaluation
L1  - 
SN  - 
N1  - 
N1  - 
AB  - Motivated by the potential use of collaborative tagging systems to develop new recommender systems, we have implemented and compared three variants of user-based collaborative filtering algorithms to provide recommendations of articles on CiteULike. On our first approach, Classic Collaborative filtering (CCF), we use Pearson correlation to calculate similarity between users and a classic adjusted ratings formula to rank the recommendations. Our second approach, Neighbor-weighted Collaborative Filtering (NwCF), incorporates the amount of raters in the ranking formula of the recommendations. A modified version of the Okapi BM25 IR model over users ’ tags is implemented on our third approach to form the user neighborhood. Our results suggest that incorporating the number of raters into the algorithms leads to an improvement of precision, and they also support that tags can be considered as an alternative to Pearson correlation to calculate the similarity between users and their neighbors in a collaborative tagging system. 
ER  -

TY  - CONF
AU  - Parra, Denis
AU  - Brusilovsky, Peter
A2  - 
T1  - Evaluation of Collaborative Filtering Algorithms for Recommending Articles on CiteULike
T2  - Proceedings of the Workshop on Web 3.0: Merging Semantic Web and Social Web
PB  - 
CY  - 
PY  - 2009/06
M2  - 
VL  - 467
IS  - 
SP  - 
EP  - 
UR  - http://ceur-ws.org/Vol-467/paper5.pdf
M3  - 
KW  - tagging
KW  - item
KW  - recommender
KW  - collaborative
KW  - social
KW  - folksonomy
KW  - filtering
L1  - 
SN  - 
N1  - 
N1  - 
AB  - Motivated by the potential use of collaborative tagging systems to develop new recommender systems, we have implemented and compared three variants of user-based collaborative filtering algorithms to provide recommendations of articles on CiteULike. On our first approach, Classic Collaborative filtering (CCF), we use Pearson correlation to calculate similarity between users and a classic adjusted ratings formula to rank the recommendations. Our second approach, Neighbor-weighted Collaborative Filtering (NwCF), incorporates the amount of raters in the ranking formula of the recommendations. A modified version of the Okapi BM25 IR model over users ’ tags is implemented on our third approach to form the user neighborhood. Our results suggest that incorporating the number of raters into the algorithms leads to an improvement of precision, and they also support that tags can be considered as an alternative to Pearson correlation to calculate the similarity between users and their neighbors in a collaborative tagging system. 
ER  -