Hybrid System for Generating Learning Object Metadata

Motelet, Olivier; Baloian, Nelson

doi:10.1109/icalt.2006.1652504

Cited by 8 publications

(6 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…La biblioteca virtual de contenidos puede ser construida a través de un esfuerzo de colaboración de expertos en el tema y de referencias bibliográficas. Los metadatos de los contenidos de aprendizaje se pueden crear de forma manual o en una forma automatizada (Motelet & Baloian, 2006).…”

Section: Algoritmo De Recomendaciónunclassified

Modelo de sistema de recomendación basado en el contexto a partir del análisis de código estático para el desarrollo del Pensamiento Computacional: Caso de Programación Web

Vera

Villalba-Condori

Cuba-Sayco

2018

Education in the Knowledge Society

View full text Add to dashboard Cite

Este trabajo propone un modelo de recomendación de contenidos educativos basado en el contexto de un usuario, el cual usa un modelo de contexto que incorpora el rol, las tareas, ejercicios de programación y su aplicación al problema de recomendación. Las recomendaciones se hacen sobre la base de la estimación de la diferencia que existe entre el nivel de conocimiento de un usuario frente a las habilidades que este requiere en el contexto en el que se encuentra. Los experimentos desarrollados en el contexto del estudiante muestran que, cuando se utiliza un modelo de razonamiento probabilístico, este modelo ayuda a obtener mejores recomendaciones de contenidos educativos, acorde con las competencias que le hacen falta a un estudiante respecto a un tema que necesita aprender. En consecuencia, se busca una estandarización para sistemas de recomendación.

show abstract

Section: Algoritmo De Recomendaciónunclassified

Modelo de sistema de recomendación basado en el contexto a partir del análisis de código estático para el desarrollo del Pensamiento Computacional: Caso de Programación Web

Vera

Villalba-Condori

Cuba-Sayco

2018

Education in the Knowledge Society

View full text Add to dashboard Cite

show abstract

“…By taking into account models of [17] [18] [19], we may evaluate the Difficulty by mean of a relationship between the concepts treated in the LO and its Duration. For a given set of concepts, the less Duration corresponds to the higher Difficulty and vice versa.…”

Section: Automatic Metadata Extractionmentioning

confidence: 99%

Automatic Extraction of Metadata from Learning Objects

Miranda

Ritrovato

2014

2014 International Conference on Intelligent Networking and Collaborative Systems

View full text Add to dashboard Cite

A good indexing of the learning objects is the better way to guarantee their reuse in the distance-learning context. We need to supply each content of a machine-understandable description including both technological and pedagogical information able to declare requirements and limits for its right use and to improve any research and delivery action. These descriptions are stored in the metadata: standard-based data structures. Filling in the metadata is a boring and timeconsuming activity but it is very important since it could influence, in the learner-centered processes, the choice of the best material to deliver. This paper describes a possible methodological approach to automate this activity by extracting metadata directly from the files setting up the learning object itself. In the literature there are many methods able to automatically characterize the technological aspects of the content (format, dimensions, HW and SW requirements, etc.) but very few of them are able to provide information about its pedagogical features (educational style, semantic density, difficulty, time to learn, interactivity level, etc.). The proposed approach tries to draw together information theory, learning models, statistical analysis and ad hoc heuristics to extract a wide set of fields of the metadata. The results of a first experimentation are particularly encouraging to think about this approach as a solution to enrich content management systems and, in particular, e-learning platforms having needs to manage wide content storage and huge amount of users with various personal features, devices for interaction and goals as in the MOOCs.

show abstract

“…American researchers also proposed for word metadata annotation method [9]. CRIS UNS achieved metadata annotation method of PDF based on machine learning [10]. MARVEL achieved semantic metadata extraction of video [11].…”

Section: Related Workmentioning

confidence: 99%

Learning Objects Automatic Generation System for Multiple Data Formats

Li¹,

Li²

2014

Proceedings of the 3rd International Conference on Computer Science and Service System

View full text Add to dashboard Cite

This paper focuses on object processing digital resources to enhance their reusability and adaptability. Deep into content level of digital resources belonging to different formats, to achieve fine-grained knowledge-based learning objects automated generation, this paper presents a MPLOG framework that integrates a variety of learning resources analyzers. Under the guidance of the domain ontology, the analyzers have divided digital resources into blocks and marked them with knowledge point.

show abstract

Hybrid System for Generating Learning Object Metadata

Abstract: Abstract

Cited by 8 publications

References 5 publications

Modelo de sistema de recomendación basado en el contexto a partir del análisis de código estático para el desarrollo del Pensamiento Computacional: Caso de Programación Web

Modelo de sistema de recomendación basado en el contexto a partir del análisis de código estático para el desarrollo del Pensamiento Computacional: Caso de Programación Web

Automatic Extraction of Metadata from Learning Objects

Learning Objects Automatic Generation System for Multiple Data Formats

Contact Info

Product

Resources

About