One standing problem in the area of web-based e-learning is how to support instructionaldesigners to effectively and efficiently retrieve learning materials, appropriate for theireducational purposes. Learning materials can be retrieved from structured repositories,such as repositories of Learning Objects and Massive Open Online Courses; they could alsocome from unstructured sources, such as web hypertext pages. Platforms for distance educationoften implement algorithms for recommending specific educational resources andpersonalized learning paths to students. But choosing and sequencing the adequate learningmaterials to build adaptive courses may reveal to be quite a challenging task.In particular, establishing the prerequisite relationships among learning objects, in termsof prior requirements needed to understand and complete before making use of the subsequentcontents, is a crucial step for faculty, instructional designers or automated systemswhose goal is to adapt existing learning objects to delivery in new distance courses.Nevertheless, this information is often missing. In this paper, an innovative machinelearning-based approach for the identification of prerequisites between text-basedresources is proposed. A feature selection methodology allows us to consider the attributesthat are most relevant to the predictive modeling problem. These features are extractedfrom both the input material and weak-taxonomies available on the web. Input dataundergoes a Natural language process that makes finding patterns of interest more easyfor the applied automated analysis. Finally, the prerequisite identification is cast to a binarystatistical classification task. The accuracy of the approach is validated by means of experimentalevaluations on real online coursers covering different subjects.
Prerequisites between learning objects: Automatic extraction based on a machine learning approach
Sciarrone, Filippo;
2018-01-01
Abstract
One standing problem in the area of web-based e-learning is how to support instructionaldesigners to effectively and efficiently retrieve learning materials, appropriate for theireducational purposes. Learning materials can be retrieved from structured repositories,such as repositories of Learning Objects and Massive Open Online Courses; they could alsocome from unstructured sources, such as web hypertext pages. Platforms for distance educationoften implement algorithms for recommending specific educational resources andpersonalized learning paths to students. But choosing and sequencing the adequate learningmaterials to build adaptive courses may reveal to be quite a challenging task.In particular, establishing the prerequisite relationships among learning objects, in termsof prior requirements needed to understand and complete before making use of the subsequentcontents, is a crucial step for faculty, instructional designers or automated systemswhose goal is to adapt existing learning objects to delivery in new distance courses.Nevertheless, this information is often missing. In this paper, an innovative machinelearning-based approach for the identification of prerequisites between text-basedresources is proposed. A feature selection methodology allows us to consider the attributesthat are most relevant to the predictive modeling problem. These features are extractedfrom both the input material and weak-taxonomies available on the web. Input dataundergoes a Natural language process that makes finding patterns of interest more easyfor the applied automated analysis. Finally, the prerequisite identification is cast to a binarystatistical classification task. The accuracy of the approach is validated by means of experimentalevaluations on real online coursers covering different subjects.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.