The sensitivities of user profile information in music recommender systems

E.M. Perik, B.E.R. Ruyter, de, P. Markopoulos, J.H. Eggen

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

Abstract

Personalized services can cause privacy concerns, due to the acquisition, storage and application of sensitive personal information. This paper describes empirical research into the factors influencing the trade-off between the perceived benefits of personalization and the privacy ‘costs’ experienced by individuals. The experiment in question concerns a music recommender system accessed over the Internet. Recommendations are based on two different types of information about their user: music preferences and personality. Users are offered several levels of disclosure for this information. Results show similar disclosure behavior by the users for the two types of personal information. This contradicts attitudes of users as they were reported in a questionnaire and post-experiment interview. Factors that influence people’s disclosure behavior are the amount and clarity of information regarding the purpose of the information disclosure and regarding who gets access to the information, the degree of confidentiality of the information involved and the benefits people expect to gain from disclosing personal information.
Original languageEnglish
Title of host publicationSecond Annual Conference on Privacy, Security and Trust, Fredericton, October 13-15, 2004
Place of PublicationBrunswick, Canada
Pages137-141
Publication statusPublished - 2006
Eventconference; PST'04 : privacy, security and trust : 2nd annual conference; 2004-10-13; 2004-10-15 -
Duration: 13 Oct 200415 Oct 2004

Conference

Conferenceconference; PST'04 : privacy, security and trust : 2nd annual conference; 2004-10-13; 2004-10-15
Period13/10/0415/10/04
OtherPST'04 : privacy, security and trust : 2nd annual conference

Fingerprint Dive into the research topics of 'The sensitivities of user profile information in music recommender systems'. Together they form a unique fingerprint.

Cite this