Building profiles based on ontology for recommendation custom interfaces

Abstract

The recommendation custom data is based primarily on the users' classification, and their integration in a process to address these interests. In this very context figures our article, which is part of a series of researches conducted by our team within a build of user profiles based on Human-Computer interface (HCI) ontology for recommendation custom interfaces. The extension of this approach provides a semantic representation of the concepts of ergonomic interfaces using reference ontology HCI. In this context, we benefit from the internet users' contributions, by answering the questionnaires suggested by system. These questionnaires will be integrated within ontology of the domain of HCI ergonomics. The answers to the suggested questionnaires will allow a semantic classification of profiles according to a vector model which will be defined later. This article consists of four sections. In the first section we present personalization techniques and recommendation. Secondly we set out construction techniques of user profiles based on ontology, In the third section, we present our approach to building profiles based on ontology for a recommendation custom interfaces in order to help the system make decisions according to the centers ergonomic interest profiles, We conclude in the last section by summarizing our contribution and providing opportunities for our work.

A Systematic Review on the Application of Ontologies to Improve Career Guidance

“…The professional sector and the development of the nation have suffered as a result of the lack of appropriate CG, which has allowed parents and peers to influence students' careers (Arshad et al, 2018). In addition to having a big impact on the employment market (Abdellah et al, 2019), orienting and guiding students will also have a big impact on building a sustainable society by advancing both social and economic goals (Elyusufi et al, 2014). This is because it helps avoid skill mismatches, increases productivity, and addresses social equity and social inclusion.…”

Churn Prediction Analysis by Combining Machine Learning Algorithms and Best Features Exploration

“…Indeed, the use of relevant features with some classical machine learning models is important when carrying out the training step. This paper is a part of a series of research carried out by a team of our laboratory, interested in users profiling and related predictive analyzes [9] [10] [11]. The work is presented as follows; in the first section we present literature review of churn prediction works using machine learning models.…”