Integrating a cognitive assistant within a critique-based recommender

Abstract

Recommender systems are cognitive computing systems designed to support humans in their decision-making processes through convincing, timely product suggestions. In the field of recommender systems, critique-based recommenders have been widely applied as an effective approach for guiding users through a product space in pursuit of suitable products. To date, no critique-based approach has included an assistant that support users in their search in a pleasant way. In this paper, we describe how we integrate an assistant within a critique-based recommender. We consider the proposed assistant to be cognitive because its reasoning process when recommending products is based on a cognitively-inspired clustering algorithm. The proposal is evaluated by users and compared with a non-assistant approach. The results of this research demonstrate that the integration of a cognitive assistant within the recommender improves the user experience and increases the performance of the recommendation process, i.e., users need fewer cycles to achieve the desired product or service.