The wisdom of the few: A collaborative filtering approach based on expert opinions from the web

Xavier Amatriain, Neal Lathia, Josep M. Pujol, Haewoon Kwak, Nuria Oliver

Research output: Chapter in Book/Report/Conference proceedingConference contribution

100 Citations (Scopus)

Abstract

Nearest-neighbor collaborative filtering provides a successful means of generating recommendations for web users. However, this approach suffers from several shortcomings, including data sparsity and noise, the cold-start problem, and scalability. In this work, we present a novel method for recommending items to users based on expert opinions. Our method is a variation of traditional collaborative filtering: rather than applying a nearest neighbor algorithm to the user-rating data, predictions are computed using a set of expert neighbors from an independent dataset, whose opinions are weighted according to their similarity to the user. This method promises to address some of the weaknesses in traditional collaborative filtering, while maintaining comparable accuracy. We validate our approach by predicting a subset of the Netflix data set. We use ratings crawled from a web portal of expert reviews, measuring results both in terms of prediction accuracy and recommendation list precision. Finally, we explore the ability of our method to generate useful recommendations, by reporting the results of a user-study where users prefer the recommendations generated by our approach.

Original languageEnglish
Title of host publicationProceedings - 32nd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2009
Pages532-539
Number of pages8
DOIs
Publication statusPublished - 28 Dec 2009
Externally publishedYes
Event32nd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2009 - Boston, MA, United States
Duration: 19 Jul 200923 Jul 2009

Other

Other32nd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2009
CountryUnited States
CityBoston, MA
Period19/7/0923/7/09

Fingerprint

Collaborative filtering
Scalability
Wisdom
Expert opinion
World Wide Web

Keywords

  • Collaborative filtering
  • Cosine similarity
  • Experts
  • Nearest neighbors
  • Recommender system
  • Top-N recommendations

ASJC Scopus subject areas

  • Computer Science Applications
  • Information Systems
  • Information Systems and Management

Cite this

Amatriain, X., Lathia, N., Pujol, J. M., Kwak, H., & Oliver, N. (2009). The wisdom of the few: A collaborative filtering approach based on expert opinions from the web. In Proceedings - 32nd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2009 (pp. 532-539) https://doi.org/10.1145/1571941.1572033

The wisdom of the few : A collaborative filtering approach based on expert opinions from the web. / Amatriain, Xavier; Lathia, Neal; Pujol, Josep M.; Kwak, Haewoon; Oliver, Nuria.

Proceedings - 32nd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2009. 2009. p. 532-539.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Amatriain, X, Lathia, N, Pujol, JM, Kwak, H & Oliver, N 2009, The wisdom of the few: A collaborative filtering approach based on expert opinions from the web. in Proceedings - 32nd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2009. pp. 532-539, 32nd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2009, Boston, MA, United States, 19/7/09. https://doi.org/10.1145/1571941.1572033
Amatriain X, Lathia N, Pujol JM, Kwak H, Oliver N. The wisdom of the few: A collaborative filtering approach based on expert opinions from the web. In Proceedings - 32nd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2009. 2009. p. 532-539 https://doi.org/10.1145/1571941.1572033
Amatriain, Xavier ; Lathia, Neal ; Pujol, Josep M. ; Kwak, Haewoon ; Oliver, Nuria. / The wisdom of the few : A collaborative filtering approach based on expert opinions from the web. Proceedings - 32nd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2009. 2009. pp. 532-539
@inproceedings{f7b034ee67dd4e59b2aaa6a0afd71922,
title = "The wisdom of the few: A collaborative filtering approach based on expert opinions from the web",
abstract = "Nearest-neighbor collaborative filtering provides a successful means of generating recommendations for web users. However, this approach suffers from several shortcomings, including data sparsity and noise, the cold-start problem, and scalability. In this work, we present a novel method for recommending items to users based on expert opinions. Our method is a variation of traditional collaborative filtering: rather than applying a nearest neighbor algorithm to the user-rating data, predictions are computed using a set of expert neighbors from an independent dataset, whose opinions are weighted according to their similarity to the user. This method promises to address some of the weaknesses in traditional collaborative filtering, while maintaining comparable accuracy. We validate our approach by predicting a subset of the Netflix data set. We use ratings crawled from a web portal of expert reviews, measuring results both in terms of prediction accuracy and recommendation list precision. Finally, we explore the ability of our method to generate useful recommendations, by reporting the results of a user-study where users prefer the recommendations generated by our approach.",
keywords = "Collaborative filtering, Cosine similarity, Experts, Nearest neighbors, Recommender system, Top-N recommendations",
author = "Xavier Amatriain and Neal Lathia and Pujol, {Josep M.} and Haewoon Kwak and Nuria Oliver",
year = "2009",
month = "12",
day = "28",
doi = "10.1145/1571941.1572033",
language = "English",
isbn = "9781605584836",
pages = "532--539",
booktitle = "Proceedings - 32nd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2009",

}

TY - GEN

T1 - The wisdom of the few

T2 - A collaborative filtering approach based on expert opinions from the web

AU - Amatriain, Xavier

AU - Lathia, Neal

AU - Pujol, Josep M.

AU - Kwak, Haewoon

AU - Oliver, Nuria

PY - 2009/12/28

Y1 - 2009/12/28

N2 - Nearest-neighbor collaborative filtering provides a successful means of generating recommendations for web users. However, this approach suffers from several shortcomings, including data sparsity and noise, the cold-start problem, and scalability. In this work, we present a novel method for recommending items to users based on expert opinions. Our method is a variation of traditional collaborative filtering: rather than applying a nearest neighbor algorithm to the user-rating data, predictions are computed using a set of expert neighbors from an independent dataset, whose opinions are weighted according to their similarity to the user. This method promises to address some of the weaknesses in traditional collaborative filtering, while maintaining comparable accuracy. We validate our approach by predicting a subset of the Netflix data set. We use ratings crawled from a web portal of expert reviews, measuring results both in terms of prediction accuracy and recommendation list precision. Finally, we explore the ability of our method to generate useful recommendations, by reporting the results of a user-study where users prefer the recommendations generated by our approach.

AB - Nearest-neighbor collaborative filtering provides a successful means of generating recommendations for web users. However, this approach suffers from several shortcomings, including data sparsity and noise, the cold-start problem, and scalability. In this work, we present a novel method for recommending items to users based on expert opinions. Our method is a variation of traditional collaborative filtering: rather than applying a nearest neighbor algorithm to the user-rating data, predictions are computed using a set of expert neighbors from an independent dataset, whose opinions are weighted according to their similarity to the user. This method promises to address some of the weaknesses in traditional collaborative filtering, while maintaining comparable accuracy. We validate our approach by predicting a subset of the Netflix data set. We use ratings crawled from a web portal of expert reviews, measuring results both in terms of prediction accuracy and recommendation list precision. Finally, we explore the ability of our method to generate useful recommendations, by reporting the results of a user-study where users prefer the recommendations generated by our approach.

KW - Collaborative filtering

KW - Cosine similarity

KW - Experts

KW - Nearest neighbors

KW - Recommender system

KW - Top-N recommendations

UR - http://www.scopus.com/inward/record.url?scp=72449179929&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=72449179929&partnerID=8YFLogxK

U2 - 10.1145/1571941.1572033

DO - 10.1145/1571941.1572033

M3 - Conference contribution

AN - SCOPUS:72449179929

SN - 9781605584836

SP - 532

EP - 539

BT - Proceedings - 32nd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2009

ER -