weHelp: A Reference Architecture for Social Recommender Systems

Recommender systems have become increasingly popular. Most of the research on recommender systems has focused on recommendation algorithms. There has been relatively little research, however, in the area of generalized system architectures for recommendation systems. In this paper, we introduce weHelp: a reference architecture for social recommender systems - systems where recommendations are derived automatically from the aggregate of logged activities conducted by the system's users. Our architecture is designed to be application and domain agnostic. We feel that a good reference architecture will make designing a recommendation system easier; in particular, weHelp aims to provide a practical design template to help developers design their own well-modularized systems.

[1]  Alexander Felfernig,et al.  Consumer decision making in knowledge-based recommendation , 2009, Journal of Intelligent Information Systems.

[2]  Tanguy Coenen,et al.  Knowledge Sharing over Social Networking Systems: Architecture, Usage Patterns and Their Application , 2006, OTM Workshops.

[3]  Douglas B. Terry,et al.  Using collaborative filtering to weave an information tapestry , 1992, CACM.

[4]  Gerhard Widmer,et al.  Learning in the Presence of Concept Drift and Hidden Contexts , 1996, Machine Learning.

[5]  Christopher Meek,et al.  Tied boltzmann machines for cold start recommendations , 2008, RecSys '08.

[6]  Licia Capra,et al.  Social ranking: uncovering relevant content using tag-based recommender systems , 2008, RecSys '08.

[7]  Pearl Pu,et al.  A recursive prediction algorithm for collaborative filtering recommender systems , 2007, RecSys '07.

[8]  Gail E. Kaiser,et al.  Retina: helping students and instructors based on observed programming activities , 2009, SIGCSE '09.

[9]  Aris Floratos,et al.  geWorkbench: an open source platform for integrative genomics , 2010, Bioinform..

[10]  Alfred Kobsa,et al.  A Review and Analysis of Commercial User Modeling Servers for Personalization on the World Wide Web , 2000, User Modeling and User-Adapted Interaction.

[11]  Edith Cohen,et al.  Maintaining time-decaying stream aggregates , 2006, J. Algorithms.

[12]  Gail E. Kaiser,et al.  COMPASS: A Community-driven Parallelization Advisor for Sequential Software , 2009, 2009 ICSE Workshop on Multicore Software Engineering.

[13]  Tsvi Kuflik,et al.  Enhancing privacy and preserving accuracy of a distributed collaborative filtering , 2007, RecSys '07.

[14]  Richard C. Holt,et al.  A reference architecture for Web servers , 2000, Proceedings Seventh Working Conference on Reverse Engineering.

[15]  Jing Hua,et al.  A Reference Architecture for Scientific Workflow Management Systems and the VIEW SOA Solution , 2009, IEEE Transactions on Services Computing.

[16]  Alexander Tuzhilin,et al.  The long tail of recommender systems and how to leverage it , 2008, RecSys '08.

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

[18]  Michael Twidale,et al.  Where am I and who am I?: issues in collaborative technical help , 2004, CSCW.

[19]  Mark S. Ackerman,et al.  Answer Garden 2: merging organizational memory with collaborative help , 1996, CSCW '96.

[20]  Michael J. Muller,et al.  Recommending topics for self-descriptions in online user profiles , 2008, RecSys '08.

[21]  Barbara J. Meier.  ACE: a color expert system for user interface design , 1988, UIST '88.

[22]  Jacki O'Neill,et al.  The practical indispensability of articulation work to immediate and remote help-giving , 2006, CSCW '06.

[23]  Mary Beth Rosson,et al.  Awareness and teamwork in computer-supported collaborations , 2006, Interact. Comput..

[24]  Gail E. Kaiser,et al.  genSpace: Exploring social networking metaphors for knowledge sharing and scientific collaborative work , 2008, 2008 23rd IEEE/ACM International Conference on Automated Software Engineering - Workshops.