The changing learning landscape due to digitalization, green transition, and pandemic have emphasized the need for lifelong learning and up-skilling. The increasing availability of online resources has created a demand for personalized learning experiences tailored to individual learners. While numerous systems have been developed to recommend personalized learning paths, there remains a research gap in personalizing learning materials. Customizing the learning materials’ content according to the learner’s needs and profile can guarantee engagement and motivation. This, in turn, can lead to enhanced learning outcomes and higher satisfaction with the learning experience. This paper focuses on tailoring educational materials to students’ academic background knowledge. By involving Natural Language Processing (NLP) and Network Analysis techniques we propose a novel approach to automatically extract and map knowledge concepts retained in a study course and owned by a learner. Specifically, we use Named Entity Recognition (NER) to extract knowledge concepts from the text of the record of lessons and handouts of a teaching course. Recent works have shown that NER is a promising tool for identifying entities, such as skills, from unstructured text. The record of lessons and the handouts are texts of a high level of detail, which ensures the extraction of fine-grained knowledge concepts. The extracted knowledge concepts are then used to create a glossary for a teaching course tailored to the student’s prior knowledge. Glossaries serve as a foundation for learning and, to be effective, their content needs to be tailored to the student’s prior knowledge.