Experimental analysis of the effects of social relations on mobile application recommendation

In this paper, we empirically analyze the effects of social relations on the recommendation of mobile applications in a community of students at a university. We identify three social relations by questionnaires and two relations by students properties, and examine their effects from a wide variety of perspectives in the framework of top-N recommendation by user and item based collaborative filtering with two re-ranking mechanisms. In the analysis, we assess the difference of the effects by the origin and strength of social relations as well as by the methods of collaborative filtering and re-ranking mechanisms. As a result of the analysis, we confirm that appropriate social relations can significantly improve the performance of recommendation, in terms of increasing diversity and novelty with keeping high accuracy, especially for the late adopters.

[1]  David Maxwell Chickering,et al.  Dependency Networks for Inference, Collaborative Filtering, and Data Visualization , 2000, J. Mach. Learn. Res..

[2]  Sean M. McNee,et al.  Improving recommendation lists through topic diversification , 2005, WWW '05.

[3]  Panagiotis Adamopoulos,et al.  On Unexpectedness in Recommender Systems , 2013, ACM Trans. Intell. Syst. Technol..

[4]  Thomas Hofmann,et al.  Latent Class Models for Collaborative Filtering , 1999, IJCAI.

[5]  Nathan Srebro,et al.  Fast maximum margin matrix factorization for collaborative prediction , 2005, ICML.

[6]  Mark S. Granovetter.  Threshold Models of Collective Behavior , 1978, American Journal of Sociology.

[7]  George Karypis,et al.  Evaluation of Item-Based Top-N Recommendation Algorithms , 2001, CIKM '01.

[8]  Ryohei Orihara,et al.  Metrics for Evaluating the Serendipity of Recommendation Lists , 2007, JSAI.

[9]  Jonathan L. Herlocker,et al.  Evaluating collaborative filtering recommender systems , 2004, TOIS.

[10]  Jennifer Golbeck,et al.  Generating Predictive Movie Recommendations from Trust in Social Networks , 2006, iTrust.

[11]  M. McPherson,et al.  Birds of a Feather: Homophily in Social Networks , 2001 .

[12]  John Riedl,et al.  An algorithmic framework for performing collaborative filtering , 1999, SIGIR '99.

[13]  Panagiotis Adamopoulos,et al.  On Unexpectedness in Recommender Systems: Or How to Expect the Unexpected , 2011, DiveRS@RecSys.

[14]  Ido Guy,et al.  Personalized recommendation of social software items based on social relations , 2009, RecSys '09.

[15]  John Riedl,et al.  GroupLens: an open architecture for collaborative filtering of netnews , 1994, CSCW '94.

[16]  Alex Pentland,et al.  Composite Social Network for Predicting Mobile Apps Installation , 2011, AAAI.

[17]  Luo Si,et al.  An automatic weighting scheme for collaborative filtering , 2004, SIGIR '04.

[18]  Oscar Castillo,et al.  Proceedings of the International MultiConference of Engineers and Computer Scientists 2007, IMECS 2007, March 21-23, 2007, Hong Kong, China , 2007, IMECS.

[19]  John Riedl,et al.  Item-based collaborative filtering recommendation algorithms , 2001, WWW '01.

[20]  Anju Vyas.  Print , 2003 .

[21]  Chao Liu,et al.  Recommender systems with social regularization , 2011, WSDM '11.

[22]  Hong Joo Lee,et al.  Use of social network information to enhance collaborative filtering performance , 2010, Expert Syst. Appl..

[23]  Mouzhi Ge,et al.  Beyond accuracy: evaluating recommender systems by coverage and serendipity , 2010, RecSys '10.

[24]  David Heckerman,et al.  Empirical Analysis of Predictive Algorithms for Collaborative Filtering , 1998, UAI.

[25]  George Karypis,et al.  Item-based top-N recommendation algorithms , 2004, TOIS.