New contextual collaborative filtering system with application to personalized healthy nutrition education

Nowadays, the Internet is becoming a platform of choice where the number of users and items grows dra-matically making recommender systems (RS) the most required and widespread technology. This paper deals with context aware collaborative RS and presents a double contribution that consists of a two Dimensions Contextual Collaborative Recommender System (2DCCRS) and a related application. Our first contribution proposes a new framework for collaborative context aware RS that relies on two key ideas. The first one suggests splitting the context into two parts namely internal and external contexts in order to deal with both internal and external context attributes in different and more appropriate manners. This allows addressing the complexity of the context model in a more effective way. In the second idea, we introduce two concepts; namely the Stakeholders and Aggregation to effectively alleviate the problems of new user and new item. 2DCCRS is based on a multi-layer architecture. Its highest layer relies on a pre-filtering algorithm that deals with the cold start system problem, and is mainly based on the similarity between the user profile and the items features. The middle layer is based on a collab-orative filtering algorithm that takes into account the users' preferences, interests and priorities; while the deepest layer, which is considered the most relevant in our multilayer architecture, focuses on a post-filtering algorithm in which the recommendations are much more adapted to the user environment. In Our second contribution, we present a case study of 2DCCRS in order to demonstrate the usefulness and effectiveness of the proposed approach. Indeed, we propose a personalized Healthy and Tasty appli-cation (H&T) that generates items based on 2DCCRS framework to guide the user toward the healthy and tasty meals that best meet his needs. The obtained results are very promising and show the effectiveness of our proposal.(c) 2020 The Authors. Production and hosting by Elsevier B.V. on behalf of King Saud University. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).

Automated summary

This paper introduces a double contribution of a two-dimensional context-aware collaborative recommender system (2DCCRS) and a related application. The 2DCCRS framework splits the context into internal and external parts to effectively address the complexity of the context model. It also introduces the concepts of stakeholders and aggregation to tackle the challenges of new users and new items. A case study of the 2DCCRS framework demonstrates its usefulness and effectiveness.