The Needs of the Many: A Case-Based Group Recommender System

Lecture notes in computer sciencePublished 1 January 2006

Kevin McCarthy, Lorraine McGinty, Barry Smyth, María Salamó

DOI10.1007/11805816_16

Source URL

Citations64

SJR quartileQ2

SJR score0.35

SNIP0.55

TL;DR

A (case-based) group recommender designed to meet the challenges presented by groups of inter-related users is introduced, including the generation of reactive and proactive suggestions based on user feedback in the form of critiques.

Abstract

While much of the research in the area of recommender systems has focused on making recommendations to the individual, many recommendation scenarios involve groups of inter-related users. In this paper we consider the challenges presented by the latter scenario. We introduce a (case-based) group recommender designed to meet these challenges through a variety of recommendation features, including the generation of reactive and proactive suggestions based on user feedback in the form of critiques, and demonstrate its effectiveness through a live-user case-study.

Keywords

Computer Science

Lecture notes in computer scienceAdvances in Case-Based Reasoning

649 Citations1996Ian F. C. Smith, Boi Faltings

This book is referred to read because it is an inspiring book to give you more chance to get experiences and also thoughts and this advances in case based reasoning.

IEEE ExpertThe FindMe approach to assisted browsing

346 Citations1997Robin Burke, Kristian J. Hammond +1 more

This article illustrates the idea of instance-based browsing, which involves structuring retrieval around the critiquing of previously retrieved examples, and retrieval strategies, or knowledge-based heuristics for finding relevant information, with examples of working FindMe systems.

More than the sum of its members

253 Citations2004Anthony Jameson

Four issues concerning the design of suitable preference elicitation and aggregation methods and ways of making members aware of each other's preferences and motivational orientations, such as the use of animated representatives of group members are identified.

Intelligent profiling by example

123 Citations2001Sybil Shearin, Henry Lieberman

The Apt Decision agent learns user preferences in the domain of rental real estate by observing the user's critique of apartment features, and uses interactive learning techniques to build a profile of user preferences, which can be saved and used in further retrievals.

eCite Digital Repository (University of Tasmania)CATS: A Synchronous Approach to Collaborative Group Recommendation

123 Citations2006Kevin McCarthy, María Salamó +4 more

This paper introduces a group recommender system that is designed to provide assistance to a group of friends trying the plan a skiing vacation and describes how personal and shared profiles and interaction spaces can be managed to generate sets of recommendations for the individual as well as the group.

Knowledge-Based SystemsIncremental critiquing

97 Citations2005J.P. Reilly, Kevin McCarthy +2 more

An approach to critiquing is described that attempts to consider a user's Critiquing history, as well as their current critique, when making new recommendations, which has the potential to significantly improve recommendation efficiency.

Artificial Intelligence ReviewInteractive Critiquing forCatalog Navigation in E-Commerce

78 Citations2002Robin Burke

An interactive, incremental, case-based, critiquing approach to solving the problem of e-commerce catalogs, whichphasizes products over features or constraints, and uses case- based reasoning techniques for its product retrieval.

Lecture notes in computer scienceDynamic Critiquing

72 Citations2004J.P. Reilly, Kevin McCarthy +2 more

A technique for automatically generating useful compound critiques over multiple case features is described and it is demonstrated how this can significantly improve the performance of a conversational recommender system.

Designing example-critiquing interaction

61 Citations2004Boi Faltings, Pearl Pu +2 more

The essential design question in example critiquing is what examples to show users in order to best help them locate their most preferred solution and this paper analyzes this question based on two requirements.

ConstraintsDecision Tradeoff Using Example-Critiquing and Constraint Programming

51 Citations2004Pearl Pu, Boi Faltings

It is shown how to integrate the constraint-based preference model with an interaction model called example-critiquing, which offers significant advantages over the commonly used ranked-list model, especially when the decision problem becomes complex.

View PDF