An Integrated Perspective of User Evaluating Personalized Recommender Systems : Performance-Driven or User-Centric

온라인에서 추천시스템은 사용자들의 구매 이력 또는 선호도를 바탕으로 적절한 콘텐츠 또는 서비스를 제공하는 IT기술이다. 추천시스템에 대한 사용자의 평가에는 추천 결과에 기반한 시스템 성과와 추천 방식에 의해 형성되는 사용자의 태도에 대한 두 측면 모두 고려되어야 한다. 그러나 시스템 성과와 사용자 태도에 대한 통합적 관점의 추천시스템 평가에 대한 연구는 많지 않았다. 본 연구의 목적은 추천시스템에 대한 사용자 평가의 통합적 관점을 제시하는 것에 있다. 그에 따라 사용자 태도 형성과 관련하여 자기 참조(Self-reference)와 사회적 실재감(Social Presence)의 정도를 구분하여 웹 기반 실험을 수행하였으며 추천시스템의 성과 측정을 위하여 추천 알고리즘 평가에 널리 활용되어 온 정확성(Accuracy)과 새로움(Novelty)을 활용하였다. 연구의 결과로 추천시스템의 사용자 만족에 미치는 변수로 정확성과 새로움이 시스템 특성 요소로 제시되었으며 사용자 태도 관점에서 사회적 실재감이 사용자의 만족에 영향을 주었다. 【This study focused on user evaluation for personalized recommender systems with the integrated view of performance of the system and user attitude of recommender systems. Since users' evaluations of recommender systems can be affected by recommendation outcomes and presentation methods, both system performances based on outcomes and user attitudes formed by the presentation methods should be considered when explaining users' evaluations. However, an integrated view of system performance and user attitudes has not been applied to explain users' evaluation of recommender systems. Thus, the goal of this study is to explain users' evaluations of recommender systems under the integrated view of predictive features and explanation features at the same time. Our findings suggest that social presence, both accuracy and noveltyhave impacts onuser satisfaction for recommender systems. Especially, predictive features including accuracy and novelty affected user satisfaction. Novelty as well as accuracy is one of the significant factors for user satisfaction while recommender systems provided usual items users have experienced when systems provide serendipitous items. Likewise, explanation features with social presence and self-reference were important for user evaluation of personalized recommender systems. For explanation features, while social presence appears as one of important factors to user satisfaction of evaluating personalized recommendations, self-reference has no significant effect on user's satisfaction for recommender systems when compared to the result of social presence. Self-referencing messages did not affect user satisfaction but the levels of self-referencing are different between low and high groups in the experiment.】

[1]  Joan Meyers-Levy,et al.  Moderators of the Impact of Self-Reference on Persuasion , 1996 .

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

[3]  J. E. Swan,et al.  Equity and Disconfirmation Perceptions as Influences on Merchant and Product Satisfaction , 1989 .

[4]  Li Chen,et al.  A user-centric evaluation framework for recommender systems , 2011, RecSys '11.

[5]  David Jingjun Xu,et al.  The Influence of Personalization in Affecting Consumer Attitudes toward Mobile Advertising in China , 2006, J. Comput. Inf. Syst..

[6]  Jennifer Edson Escalas Self-Referencing and Persuasion: Narrative Transportation versus Analytical Elaboration , 2007 .

[7]  Gerald Häubl,et al.  "Double Agents": Assessing the Role of Electronic Product Recommendation Systems , 2005 .

[8]  Paul Resnick,et al.  Recommender systems , 1997, CACM.

[9]  Hong Joo Lee,et al.  The Influence of Social Presence on Customer Intention to Reuse Online Recommender Systems: The Roles of Personalization and Product Type , 2011, Int. J. Electron. Commer..

[10]  Rama Chellappa,et al.  An electronic infrastructure for a virtual university , 1997, CACM.

[11]  Milena M. Head,et al.  The Impact of Infusing Social Presence in the Web Interface: An Investigation Across Product Types , 2005, Int. J. Electron. Commer..

[12]  Shuk Ying Ho,et al.  The attraction of personalized service for users in mobile commerce: an empirical study , 2002, SECO.

[13]  François Fouss,et al.  Evaluating Performance of Recommender Systems: An Experimental Comparison , 2008, 2008 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology.

[14]  Fred D. Davis Perceived Usefulness, Perceived Ease of Use, and User Acceptance of Information Technology , 1989, MIS Q..

[15]  Izak Benbasat,et al.  Research Note: The Influence of Recommendations and Consumer Reviews on Evaluations of Websites , 2006, Inf. Syst. Res..

[16]  Moez Limayem,et al.  E-Mail and V-Mail Usage: Generalizing Across Technologies , 2000, J. Organ. Comput. Electron. Commer..

[17]  C. Moorman Organizational Market Information Processes: Cultural Antecedents and New Product Outcomes , 1995 .

[18]  Hong Joo Lee,et al.  Mobile push personalization and user experience , 2008, AI Commun..

[19]  Hong Joo Lee,et al.  The Influence of Social Presence on Evaluating Personalized Recommender Systems , 2009, PACIS.

[20]  Valerie J. Trifts,et al.  Consumer Decision Making in Online Shopping Environments: The Effects of Interactive Decision Aids , 2000 .

[21]  Miles Hewstone,et al.  Social-influence processes of control and change:conformity, obedience to authority, and innovation , 2003 .

[22]  Izak Benbasat,et al.  The Effects of Process and Outcome Similarity on Users' Evaluations of Decision Aids , 2008, Decis. Sci..

[23]  Gediminas Adomavicius,et al.  Personalization technologies , 2005, Commun. ACM.

[24]  Thomas Kramer The Effect of Measurement Task Transparency on Preference Construction and Evaluations of Personalized Recommendations , 2006 .

[25]  Ofer Arazy,et al.  A Theory-Driven Design Framework for Social Recommender Systems , 2010, J. Assoc. Inf. Syst..

[26]  Khaled Hassanein,et al.  The Impact of Infusing Social Presence in the Web Interface : An Investigation Across Different Products ” , 2006 .

[27]  Hong Joo Lee,et al.  Understanding collaborative filtering parameters for personalized recommendations in e-commerce , 2007, Electron. Commer. Res..

[28]  Gediminas Adomavicius,et al.  Personalization technologies: A process-oriented perspective , 2006, Wirtschaftsinf..

[29]  Wynne W. Chin The partial least squares approach for structural equation modeling. , 1998 .

[30]  D. Gefen,et al.  Consumer trust in B2C e-Commerce and the importance of social presence: experiments in e-Products and e-Services , 2004 .

[31]  Detmar W. Straub,et al.  Trust and TAM in Online Shopping: An Integrated Model , 2003, MIS Q..

[32]  Francesco Ricci,et al.  Mobile Recommender Systems , 2010, J. Inf. Technol. Tour..

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

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

[35]  Izak Benbasat,et al.  Recommendation Agents for Electronic Commerce: Effects of Explanation Facilities on Trusting Beliefs , 2007, J. Manag. Inf. Syst..

[36]  Robin D. Burke,et al.  Hybrid Recommender Systems: Survey and Experiments , 2002, User Modeling and User-Adapted Interaction.

[37]  Izak Benbasat,et al.  The Effects of Personalizaion and Familiarity on Trust and Adoption of Recommendation Agents , 2006, MIS Q..

[38]  Herman Lam,et al.  Constraint-based brokering (CBB) for publishing and discovery of web services , 2007, Electron. Commer. Res..

[39]  Rashmi R. Sinha,et al.  Comparing Recommendations Made by Online Systems and Friends , 2001, DELOS.

[40]  Greg Linden,et al.  Amazon . com Recommendations Item-to-Item Collaborative Filtering , 2001 .

[41]  T. B. Rogers,et al.  Self-reference and the encoding of personal information. , 1977, Journal of personality and social psychology.

[42]  Sriram Thirumalai,et al.  Customization Strategies in Electronic Retailing: Implications of Customer Purchase Behavior , 2009, Decis. Sci..

[43]  Izak Benbasat,et al.  E-Commerce Product Recommendation Agents: Use, Characteristics, and Impact , 2007, MIS Q..

[44]  R. E. Burnkrant,et al.  Effects of Self-Referencing on Persuasion , 1995 .

[45]  Kirsten Swearingen,et al.  Beyond Algorithms: An HCI Perspective on Recommender Systems , 2001 .

[46]  T. S. Robertson,et al.  Imaging and analyzing in response to new product advertising , 1993 .

[47]  Guy Shani,et al.  Evaluating Recommendation Systems , 2011, Recommender Systems Handbook.

[48]  Shuk Ying Ho,et al.  Web Personalization as a Persuasion Strategy: An Elaboration Likelihood Model Perspective , 2005, Inf. Syst. Res..

[49]  Shuk Ying Ho,et al.  Understanding the Impact of Web Personalization on User Information Processing and Decision Outcomes , 2006, MIS Q..

[50]  M. Holbrook Introduction: the Esthetic Imperative in Consumer Research , 1981 .

[51]  C. Fornell,et al.  Evaluating structural equation models with unobservable variables and measurement error. , 1981 .

[52]  Dianne Cyr,et al.  The role of social presence in establishing loyalty in e-Service environments , 2007, Interact. Comput..

[53]  Yi-Cheng Ku,et al.  Personalized Content Recommendation and User Satisfaction: Theoretical Synthesis and Empirical Findings , 2006, J. Manag. Inf. Syst..

[54]  Leslie P. Willcocks,et al.  Analysing four types of IT sourcing decisions in the context of scale, client/supplier interdependency and risk mitigation , 1998, Inf. Syst. J..

[55]  J. M. Kittross The measurement of meaning , 1959 .