Knowledge Graphs for Representing Knowledge Progression of Students across Heterogeneous Learning Systems
Saved in:
| Title: | Knowledge Graphs for Representing Knowledge Progression of Students across Heterogeneous Learning Systems |
|---|---|
| Language: | English |
| Authors: | Soumya M. D. (ORCID |
| Source: | International Journal of Artificial Intelligence in Education. 2025 35(4):1695-1723. |
| Availability: | Springer. Available from: Springer Nature. One New York Plaza, Suite 4600, New York, NY 10004. Tel: 800-777-4643; Tel: 212-460-1500; Fax: 212-460-1700; e-mail: customerservice@springernature.com; Web site: https://link.springer.com/ |
| Peer Reviewed: | Y |
| Page Count: | 29 |
| Publication Date: | 2025 |
| Document Type: | Journal Articles Reports - Research |
| Education Level: | Higher Education Postsecondary Education |
| Descriptors: | Learning Processes, Learning Trajectories, Graphs, Knowledge Level, Computer Science Education, College Students, Foreign Countries |
| Geographic Terms: | India |
| DOI: | 10.1007/s40593-024-00434-w |
| ISSN: | 1560-4292 1560-4306 |
| Abstract: | Student models are inevitable in any educational system for analysis, reasoning, and making decisions. Courses and lessons from multiple heterogeneous learning systems may be present in the entire learning trajectory of students. So, the knowledge states of the students and domain knowledge from various learning systems need to be collated to guide the students through their learning path. Addressing this issue, we propose a 3-layer "Student Knowledge Graph" as an advancement of the educational Domain Knowledge Graphs to represent the knowledge progression of students. The first two layers of the Student KG are a semantic network of the performance history of students, and "Knowledge Components" from multiple learning systems. A knowledge layer of public knowledge base and domain ontology was added to interconnect the "Knowledge Components" of various learning systems by linking them to the entities of the knowledge layer. The results show that a clear and precise description of the "Knowledge Components" produces better connectivity between learning systems and the knowledge layer through text-based entity linking. To demonstrate the applicability of "Student Knowledge Graph," the knowledge gaps of the Computer Science students of a University system in India were analyzed, and the remedial recommendations were generated from self-paced learning system datasets. We submit that including the knowledge states of the students in educational knowledge graphs provides an effective ranking and, thereby, personalized recommendations when compared to Educational Domain Knowledge Graphs. |
| Abstractor: | As Provided |
| Entry Date: | 2026 |
| Accession Number: | EJ1499024 |
| Database: | ERIC |
| Abstract: | Student models are inevitable in any educational system for analysis, reasoning, and making decisions. Courses and lessons from multiple heterogeneous learning systems may be present in the entire learning trajectory of students. So, the knowledge states of the students and domain knowledge from various learning systems need to be collated to guide the students through their learning path. Addressing this issue, we propose a 3-layer "Student Knowledge Graph" as an advancement of the educational Domain Knowledge Graphs to represent the knowledge progression of students. The first two layers of the Student KG are a semantic network of the performance history of students, and "Knowledge Components" from multiple learning systems. A knowledge layer of public knowledge base and domain ontology was added to interconnect the "Knowledge Components" of various learning systems by linking them to the entities of the knowledge layer. The results show that a clear and precise description of the "Knowledge Components" produces better connectivity between learning systems and the knowledge layer through text-based entity linking. To demonstrate the applicability of "Student Knowledge Graph," the knowledge gaps of the Computer Science students of a University system in India were analyzed, and the remedial recommendations were generated from self-paced learning system datasets. We submit that including the knowledge states of the students in educational knowledge graphs provides an effective ranking and, thereby, personalized recommendations when compared to Educational Domain Knowledge Graphs. |
|---|---|
| ISSN: | 1560-4292 1560-4306 |
| DOI: | 10.1007/s40593-024-00434-w |
