Automatic topic terms identification from OER
Verónica Segarra-Faggioni, Audrey Romero-Peláez · 2023
Currently, there are valuable educational materials in digital format need to be analyzed automatically about covered topics. OER metadata about covered topics is essentially required by learners to build effective learning pathways towards their individual learning objectives. Using natural language processing techniques, topic terms can be automatically identified from metadata OER. Topic modeling allows identifying topics automatically from a set of documents. Based on the LDA model, we propose an automatic topic terms identification from OERs. A total of 4142 OER about “Information Technology” were collected from SkillsCommons. Finally, to identify the best experiment, we used the values of coherence and the distance inter-topic. Results reveal that discovered topics can help to improve the accessibility, discoverability, and usefulness of open educational resources. In addition to supporting the development of more effective and efficient teaching and learning practices.