A Single Strong Disagreement Ruins a Recommender: Improving Recommendation Accuracy with a Simple Statistic

A Single Strong Disagreement Ruins a Recommender: Improving Recommendation Accuracy with a Simple Statistic

Cached

Download Links

[hcil.cs.umd.edu]

by Jennifer Golbeck

BibTeX

@MISC{Golbeck_asingle,
    author = {Jennifer Golbeck},
    title = {A Single Strong Disagreement Ruins a Recommender: Improving Recommendation Accuracy with a Simple Statistic},
    year = {}
}

Bookmark

OpenURL

Abstract

Research on the use of social trust relationships for collaborative filtering has shown that trust-based recommendations can outperform traditional methods in certain cases. This, in turn, lead to insights that tie trust to certain more subtle types of similarity between users which is not captured in the overall similarity measures normally used for making recommendations. In this study, we investigate the use these trust-inspired nuanced similarity measures directly for making recommendations. After describing previous research that identified these similarity statistics, we present an experiment run on two data sets: FilmTrust and Movie-Lens. Our results show that using a simple measure-the single largest difference between users- as a weight produces significantly more accurate results than a traditional collaborative filtering algorithm and in some cases also outperforms a model-based approach. Author Keywords recommender systems, collaborative filtering, profile similarity, trust ACM Classification Keywords

Citations

774	Empirical Analysis of Predictive Algorithms for Collaborative Filtering - Breese, Heckerman, et al. - 1998
577	Using collaborative filtering to weave an information tapestry - Goldberg, Nichols, et al. - 1992
480	Applying Collaborative Filtering to Usenet News - Konstan, Miller, et al. - 1997
479	Item-based collaborative filtering recommendation algorithms - Sarwar, Karypis, et al.
388	An Algorithmic Framework for Performing Collaborative Filtering - Herlocker, Konstan, et al. - 1999
365	J.T.: Evaluating collaborative filtering recommender systems - Herlocker, Konstan, et al.
206	Explaining collaborative filtering recommendations - Herlocker, Konstan, et al. - 2000
199	Recommendation as classification: using social and content-based information in recommendation - Basu, Hirsh, et al. - 1998
169	J.T.: Application of dimensionality reduction in recommender system – a case study - Sarwar, Karypis, et al. - 2000
147	Latent semantic models for collaborative filtering - Hofmann - 2000
127	D.P.F.: Clustering methods for collaborative filtering - Ungar - 1998
80	Weighted low-rank approximations - Srebro, Jaakkola - 2003
73	Spreading Activation Models for Trust Propagation - Ziegler, Lausen - 2004
62	Trust in recommender systems - O’Donovan, Smyth - 2005
45	Using trust in recommender systems: an experimental analysis. Trust Management - Massa, Bhattacharjee - 2004
41	MovieLens unplugged: experiences with an occasionally connected recommender system - Miller, Albert, et al. - 2003
37	Unifying user-based and item-based collaborative filtering approaches by similarity fusion - Wang, Vries, et al. - 2006
33	Z.: Scalable collaborative filtering using cluster-based smoothing - Xue, Lin, et al. - 2005
30	Generating predictive movie recommendations from trust in social networks - Golbeck - 2006
28	A scalable collaborative filtering framework based on co-clustering - George, Merugu - 2005
22	Investigating correlations of trust and interest similarity-do birds of a feather really flock together. Decision Support Systems - Ziegler, Golbeck - 2005
20	Feature Weighting and Instance Selection for Collaborative Filtering: An Information-Theoretic Approach - Yu, Wen, et al. - 2003
20	Analyzing correlation between trust and user similarity in online communities - Ziegler, Lausen - 2004
15	A Bayesian model for collaborative filtering - Chen, George - 2000
14	An automatic weighting scheme for collaborative filtering - Jin, Chai, et al. - 2004
13	Towards decentralized recommender systems - Ziegler - 2005
12	J.-D.: Preference-based search and machine learning for collaborative filtering: the ‘film-conseil’ movie recommender system - Perny, Zucker - 2001
9	M.R.: Effective missing data prediction for collaborative filtering - Ma, King, et al. - 2007
8	Accounting for taste: using profile similarity to improve recommender systems - Bonhard, Harries, et al. - 2006
7	Semantic feedback for hybrid recommendations in recommendz - Garden, Dudek - 2005
3	HÖLLERER T.: Peerchooser: visual interactive recommendation - O’DONOVAN, SMYTH, et al.