Knowledge Graph-based Core Concept Identification in Learning Resources

in 8th Joint International Conference, JIST 2018, Awaji, Japan, November 26–28, 2018, Proceedings (2018, December)

The automatic identification of core concepts addressed by a learning resource is an important task in favor of organizing content for educational purposes and for the next generation of learner support ... [more ▼]

The automatic identification of core concepts addressed by a learning resource is an important task in favor of organizing content for educational purposes and for the next generation of learner support systems. We present a set of strategies for core concept identification on the basis of a semantic representation built using the open and available knowledge in the so-called Knowledge Graphs (KGs). Different unsupervised weighting strategies, as well as a supervised method that operates on the semantic representation, were implemented for core concept identification. In order to test the effectiveness of the proposed strategies, a human-expert annotated dataset of 96 learning resources extracted from MOOCs was built. In our experiments, we show the capacity of the semantic representation for the core-concept identification task as well as the superiority of the supervised method. [less ▲]

Knowledge Graph-based Teacher Support for Learning Material Authoring

in Advances in Computing - CCC 2018 (2018, September 26)

Preparing high-quality learning material is a time-intensive, yet crucial task for teachers of all educational levels. In this paper, we present SoLeMiO, a tool to recommend and integrate learning ... [more ▼]

Preparing high-quality learning material is a time-intensive, yet crucial task for teachers of all educational levels. In this paper, we present SoLeMiO, a tool to recommend and integrate learning material in popular authoring software. As teachers create their learning material, SoLeMiO identifies the concepts they want to address. In order to identify relevant concepts in a reliable, automatic and unambiguous way, we employ state of the art concept recognition and entity linking tools. From the recognized concepts, we build a semantic representation by exploiting additional information from Open Knowledge Graphs through expansion and filtering strategies. These concepts and the semantic representation of the learning material support the authoring process in two ways. First, teachers will be recommended related, heterogeneous resources from an open corpus, including digital libraries, domain-specific knowledge bases, and MOOC platforms. Second, concepts are proposed for semi-automatic tagging of the newly authored learning resource, fostering its reuse in different e-learning contexts. Our approach currently supports resources in English, French, and Spanish. An evaluation of concept identification in lecture video transcripts and a user study based on the quality of tag and resource recommendations yielded promising results concerning the feasibility of our technique. [less ▲]