Case-based recommender systems

Abstract

We describe recommender systems and especially case-based recommender systems. We define a framework in which these systems can be understood. The framework contrasts collaborative with case-based, reactive with proactive, single-shot with conversational, and asking with proposing. Within this framework, we review a selection of papers from the case-based recommender systems literature, covering the development of these systems over the last ten years.

A New Sentiment Case-Based Recommender

“…The collaborative filtering approach recommends items that do not exist in the active user's profile but those that other users have rated highly. In contrast, the content-based approach makes recommendations based on the item's similarity to previous items liked by the target user, without directly relying on the preferences of other users [1], [2]. The collaborative filtering approach recognizes users whose preferences are similar to those of a particular user and recommends items they have liked whereas the content-based approach recommends items similar to those a particular user has liked in the past [9].…”

“…Then, CBR retains the positive problem-solving experiences for further reuse. All of these processes make up the traditional 4R processes of CBR: retrieve, reuse, revise, and retain [2], [10], [11]. This knowledge may be reused when required without applying the entire procedure from scratch, or when highlighting a procedure that should be eliminated in a similar problem.…”

“…Therefore, this approach has proven to be very successful in many e-commerce sites, owing to the clear organization of users' needs and preferences ( Fig. 1) [1], [2]. The main benefit of using CBR in product recommendation is the capability to recommend alternatives that may be suitable if the system cannot find a solution that accurately matches a user's query [12].…”

Comparative Preferences Induction Methods for Conversational Recommenders

“…Generally speaking, people do not state their preferences up-front because initially they only have a vague idea of the product they would like to have [5]. Usually, criteria about the product the customer would like to purchase are specified during the dialogue with the seller.…”

“…Conversational recommender systems [5] recognise that their users may be willing and able to provide more information on their constraints and preferences, over a dialogue. The main difference with the single-shot recommendation scenario is that in the case where the user is not satisfied she can revise her request.…”