Educational Resources Recommender System for Teachers: Why and How?

Abstract Due to the large amount of data that is available on the Web, it has become increasingly difficult to locate educational resources that satisfy specific learning needs. Furthermore, the searching process can become increasingly frustrating, time-consuming and little accurate when users do not know how to perform a search. Recommender systems aim at reducing this burden by predicting and recommending users relevant elements of interest. In the educational domain, recommender systems can take advantage of user cognitive states and emotions to generate more personalized recommendations. This work proposes EduRecomSys, an educational recommender system that combines collaborative filtering with emotion detection techniques to suggest users educational resources based on the preferences/interests of other users and the user’s emotion previously detected through face recognition technologies. Likewise, EduRecomSys allows users to retrieve educational resources from multiple sources, including social networks, linked data and learning object repositories. EduRecomSys was evaluated in qualitative and quantitative terms. The qualitative evaluation relied on the participation of three domain experts: a teacher, a pedagogue and a software engineer. The quantitative evaluation was conducted with the help of 20 graduate students. The evaluation results seem encouraging and suggest that EduRecomSys has the potential to provide effective support to the teaching-learning process.

Download Full-text

A Suggested Algorithm of Recommender System to Recommend crawled-Web Open Educational Resources to Course Management System

The 7th International Conference on Information Technology ◽

10.15849/icit.2015.0050 ◽

2015 ◽

Author(s):

Jamil A. Itmazi ◽

Haytham W. Hijazi

Keyword(s):

Recommender System ◽

Management System ◽

Open Educational Resources ◽

Educational Resources ◽

Course Management System ◽

Course Management ◽

Suggested Algorithm

Download Full-text

Personalized Hybrid Educational Recommender System Using Matrix Factorization with User and Item Information

10.20944/preprints202008.0700.v1 ◽

2020 ◽

Author(s):

Paula Andrea Rodriguez-Marin ◽

Nestor Dario Duque-Mendez ◽

Demetrio Arturo Ovalle-Carranza ◽

Juan David Martinez-Vargas

Keyword(s):

Learning Style ◽

Recommender System ◽

Matrix Factorization ◽

Educational Resources ◽

Item Information ◽

Educational Environments ◽

Personalized Recommender System ◽

Online Educational Resources ◽

The Right ◽

Available Information

One of the main challenges for autonomous learning in virtual environments is finding the right material that fits students’ needs and supports their learning process. Personalized recommender systems partially solve this problem by suggesting online educational resources to students based on their preferences. However, in educational environments (which need a proper characterization of both users and educational resources), most existing recommendation algorithms either fail to include all the available information or use hybrid processes that do not exploit possible relationships between users and item features. This article presents a personalized recommender system for educational resources aimed at combining user and item information into a single mathematical model based on matrix factorization. As a result, estimated latent factors can provide insight into possible interactions between users and item features, improving the quality of the information retrieval process. We validated the proposed model on a real dataset that contains the ratings assigned by students from Universidad Nacional de Colombia and Universidade Feevale to educational resources in the Colombian Federation of Learning Object Repositories (FROAC in Spanish). User characterization included learning style and educational level, whereas item characterization (obtained from the objects’ metadata), included interactivity level, aggregation level and type, and resource format. These results, compared to those obtained when not all the available information is included, show that our method can improve the recommendation process.

Download Full-text

A Recommender System for Learning Objects Personalized Retrieval

Educational Recommender Systems and Technologies ◽

10.4018/978-1-61350-489-5.ch008 ◽

2012 ◽

pp. 182-210 ◽

Cited By ~ 10

Author(s):

Ana Casali ◽

Valeria Gerling ◽

Claudia Deco ◽

Cristina Bender

Keyword(s):

Recommender System ◽

User Profile ◽

Learning Objects ◽

Educational Resources ◽

Agent Architecture ◽

Profile Data ◽

Personalized Search ◽

Content Based Retrieval ◽

Multi Agent ◽

The Subject

This chapter describes the development of a recommender system of learning objects. This system helps a user to find educational resources that are most appropriate to his/her needs and preferences. The search is performed in different repositories of learning objects, where each object has descriptive metadata. Metadata is used to retrieve objects that satisfy not only the subject of the query, but also the user profile, taking into account his/her characteristics and preferences. A multi-agent architecture that includes several types of agents with different functionalities is used. In this chapter, we describe the modelization of the Personalized Search Agent (PS-Agent) as a graded BDI (Belief-Desire-Intention) agent. This agent is responsible for making a flexible content-based retrieval and provides an ordered list of the resources that better meet the user profile data. A prototype was implemented, and experimentation results are presented.

Download Full-text