Paula Andrea Rodríguez Marín

Multi-agent system for Knowledge-based recommendation of Learning Objects

Learning Object (LO) is a content unit being used within virtual learning environments, which -once found and retrieved- may assist students in the teaching - learning process. Such LO search and retrieval are recently supported and enhanced by data mining techniques. In this sense, clustering can be used to find groups holding similar LOs so that from obtained groups, knowledge-based recommender systems (KRS) can recommend more adapted and relevant LOs. In particular, prior knowledge come from LOs previously selected, liked and ranked by the student to whom the recommendation will be performed. In this paper, we present a KRS for LOs, which uses a conventional clustering technique, namely K-means, aimed at finding similar LOs and delivering resources adapted to a specific student. Obtained promising results show that proposed KRS is able to both retrieve relevant LO and improve the recommendation precision. Learning Object (LO) is a content unit being used within virtual learning environments, which -once found and retrieved- may assist students in the teaching - learning process. Such LO search and retrieval are recently supported and enhanced by data mining techniques. In this sense, clustering can be used to find groups holding similar LOs so that from obtained groups, knowledge-based recommender systems (KRS) can recommend more adapted and relevant LOs. In particular, prior knowledge come from LOs previously selected, liked and ranked by the student to whom the recommendation will be performed. In this paper, we present a KRS for LOs, which uses a conventional clustering technique, namely K-means, aimed at finding similar LOs and delivering resources adapted to a specific student. Obtained promising results show that proposed KRS is able to both retrieve relevant LO and improve the recommendation precision.

A New Generation of Learning Object Repositories Based on Cloud Computing

This work presents a proposal for an architecture based on a cloud computing paradigm that will permit the evolution of current learning resource repositories. This study presents current problems (heterogeneity, interoperability and low performance) of existing repositories, as well as how the proposed model will try to solve them.

Educational Resources Recommendation System for a heterogeneous Student Group

In a face-class, where the student group is heterogeneous, it is necessary to select the most appropriate educational resources that support learning for all. In this sense, multi-agent system (MAS) can be used to simulate the features of the students in the group, including their learning style, in order to help the professor find the best resources for your class. In this paper, we present MAS to educational resources recommendation for group students, simulating their profiles and selecting resources that best fit. Obtained promising results show that proposed MAS is able to delivered educational resources for a student group.

Recomendación de Estrategias de Aprendizaje Personalizadas Basadas en el Test de CHAEA

Generally, the educational strategies that apply to a group of students are the same, without addressing the fact that all students learn and process information differently. As an alternative to this situation, this article presents a proposal aimed at defining various activities that support pedagogical strategies and attend to the specific characteristics of students, especially learning style. A content-based recommendation system was implemented that, based on the students learning style obtained through CHAEA, determines and recommends activities according to the strategies that best fit the students profile. The proposal was validated in two (2) university institutions in Colombia and in dissimilar subjects; The results are promising and can be applied in different courses and in virtual, blended and classroom environments.

Intelligent Personal Assistant for Educational Material Recommendation Based on CBR

Personal assistants are focused on helping users with various tasks in the daily management, as they anticipate their needs and learn with their interaction. An intelligent personal assistant is a software agent that can perform actions requested by a user and can access to information from remote sources, based on requirements or user profile. Moreover, intelligence personal assistants can be considered as a special case of recommendation systems since they are used in web searches. Thus, the personal assistant interacts and represents users to choose relevant items according to their needs and preferences. This work proposes an intelligent personal assistant aimed to support users for selecting educational material from learning objects repositories. In this regard, a recommendation system was implemented based on the artificial intelligence technique known as CBR. The possibility of taking advantage of previous results of students with similar characteristics allows to improve the relevance of the materials for each particular student. The results of the functional tests are satisfactory.

Construction of learning objects with Augmented Reality: An experience in secondary education

One of the technologies that has been showing possibilities of application in educational environments is the Augmented Reality (AR), in addition to its application to other fields such as tourism, advertising, video games, among others. The present article shows the results of an experiment carried out at the National University of Colombia, with the design and construction of augmented learning objects for the seventh and eighth grades of secondary education, which were tested and evaluated by students of a school in the department of Caldas. The study confirms the potential of this technology to support educational processes represented in the creation of digital resources for mobile devices. The development of learning objects in AR for mobile devices can support teachers in the integration of information and communication technologies (ICT) in the teaching-learning processes.

Comparative analysis of similarity metrics for the collaborative recommendation of learning objects

Collaborative filtering based recommendation systems are based on the premise that if a user looks like another (similar) and that one liked an item, this one will like it too. The collaborative recommendations are made every day in different domains, education is not alien to it because everyday students have access to more educational resources and collaborative recommendations help find those who help in their learning process. One of the difficulties presented in implementing these systems is to determine the best metric of similarity among users among all existing to find a greater amount of similarities to the target user of the recommendation. Therefore, in this paper, we propose to perform a comparative analysis of similarity metrics for the recommendation of learning objects. Tests were conducted with university students and it was found that the overlap coefficient and the distance of the cosine, give better results when making a collaborative recommendation.

Sistema de recomendación de objetos de aprendizaje a través de filtrado colaborativo

Learning objects collaborative filtering recommender systems support students in their autonomous learning process, by finding resources that liked, interest or served a student with similar characteristics. These systems are based on the concept that if two people to be similar and one likes an item, there is a high probability that the other person also likes that item, meaning item as any material available (documents, videos, images, resources, among others). Therefore, in this paper a model is presented recommendation by collaborative filtering, where to find the similarity between users a combination of several metrics that measure this value, with the aim of finding a greater amount of similar users used. Tests were performed to a case study and the results show that the use of collaborative recommendation system delivers relevant and pertinent learning objects for students.

Adaptive framework to the search and retrieval of digital educational resources

The union between ICT and education come a great potential possibility for provide students custom environments to their needs and preferences. An alternative are adaptive systems, which require adaptation strategies and the definition of a model student, including the main characteristics of users, which will serve to make changes in the educational environment automatically. In this paper, an adaptive platform is proposed in which the specific characteristics of a user are used to perform the customized delivery of digital educational resources that are available through repositories. Some adaptations are also made in the user interfaces with educational special needs, certainly user visual disabilities.

Rules based system to educative personalized strategy recommendation according to the CHAEA test

Recommender educational strategies to students is a difficult task, as they must adapt to the way students acquire and process information. On the other hand, tests have learning styles that are mechanisms to determine the predominant style for processing student information and there selected ways. However, they have two problems that make it difficult to have a reliable result and determinate the better strategies. In this article based on rules to determine which educational strategies can recommend a student, according to the test as CHAEA and learn better each student according to their learning style system it is proposed. The proposal was validated through a case study, obtaining very good results as perceived by students.