TY  - JOUR
AU  - Gu, Xin
AU  - Sabrina, Fariza
AU  - Sohail, Shaleeza
AU  - Fan, Zongwen
PY  - 2026
DA  - 2026/03/25
TI  - Advancing Educational Data Mining through Multi-Source Data Fusion and Explainable Knowledge
JO  - ICCK Transactions on Educational Data Mining
T2  - ICCK Transactions on Educational Data Mining
JF  - ICCK Transactions on Educational Data Mining
VL  - 2
IS  - 1
SP  - 29
EP  - 32
DO  - 10.62762/TEDM.2026.793467
UR  - https://www.icck.org/article/abs/TEDM.2026.793467
KW  - educational data mining
KW  - multi-source data fusion
KW  - explainable knowledge
KW  - multi-modal learning data
KW  - personalized learning
AB  - The rapid digitalization of education has led to an explosive growth of multi-source and multi-modal learning data, providing new opportunities for advancing Educational Data Mining (EDM). By learning diverse data such as learning behaviors, assessment records, and interaction logs, EDM enables deeper insights into student learning processes and supports the development of personalized and intelligent education. However, several critical challenges remain, including the heterogeneity and fragmentation of multi-source data, the difficulty of extracting meaningful knowledge through effective data fusion, and the limited interpretability of high-performance predictive models. To address these challenges, this paper emphasizes the importance of integrating multi-source data fusion with explainable knowledge modeling. Multi-modal data fusion provides the basis for constructing comprehensive and coherent learner representations. The explainable approaches are essential for ensuring transparency, trust, and practical usability in educational settings. In particular, fuzzy knowledge representation, characterized by interpretable rules and membership functions, is important for bridging data-driven analytics and pedagogical reasoning. Fuzzy systems are the ideal candidates for explainable knowledge modeling as they combine human‑like linguistic reasoning with mathematically precise computation by allowing symbolic rules and numerical data in a transparent and interpretable way. By analyzing the key challenges and emerging directions in multi-source educational data mining, this editorial highlights the necessity of combining data integration, personalized learning, and interpretability. Such an approach enables more precise learning path design, targeted intervention, and trustworthy decision support, ultimately advancing the development of intelligent, explainable, and learner-centered educational systems.
SN  - 3070-5843
PB  - Institute of Central Computation and Knowledge
LA  - English
ER  - 

@article{Gu2026Advancing,
  author = {Xin Gu and Fariza Sabrina and Shaleeza Sohail and Zongwen Fan},
  title = {Advancing Educational Data Mining through Multi-Source Data Fusion and Explainable Knowledge},
  journal = {ICCK Transactions on Educational Data Mining},
  year = {2026},
  volume = {2},
  number = {1},
  pages = {29-32},
  doi = {10.62762/TEDM.2026.793467},
  url = {https://www.icck.org/article/abs/TEDM.2026.793467},
  abstract = {The rapid digitalization of education has led to an explosive growth of multi-source and multi-modal learning data, providing new opportunities for advancing Educational Data Mining (EDM). By learning diverse data such as learning behaviors, assessment records, and interaction logs, EDM enables deeper insights into student learning processes and supports the development of personalized and intelligent education. However, several critical challenges remain, including the heterogeneity and fragmentation of multi-source data, the difficulty of extracting meaningful knowledge through effective data fusion, and the limited interpretability of high-performance predictive models. To address these challenges, this paper emphasizes the importance of integrating multi-source data fusion with explainable knowledge modeling. Multi-modal data fusion provides the basis for constructing comprehensive and coherent learner representations. The explainable approaches are essential for ensuring transparency, trust, and practical usability in educational settings. In particular, fuzzy knowledge representation, characterized by interpretable rules and membership functions, is important for bridging data-driven analytics and pedagogical reasoning. Fuzzy systems are the ideal candidates for explainable knowledge modeling as they combine human‑like linguistic reasoning with mathematically precise computation by allowing symbolic rules and numerical data in a transparent and interpretable way. By analyzing the key challenges and emerging directions in multi-source educational data mining, this editorial highlights the necessity of combining data integration, personalized learning, and interpretability. Such an approach enables more precise learning path design, targeted intervention, and trustworthy decision support, ultimately advancing the development of intelligent, explainable, and learner-centered educational systems.},
  keywords = {educational data mining, multi-source data fusion, explainable knowledge, multi-modal learning data, personalized learning},
  issn = {3070-5843},
  publisher = {Institute of Central Computation and Knowledge}
}