Curriculum Intelligence: Leveraging Educational Data Mining to Align CS and IT Programs with Industry 5.0 Skills
Year: 2026
Type: conference-paper
Abstract: The computer science (CS) and information technology (IT) curricula play a crucial role for the graduate readiness to meet the fast changing technological challenges and increasingly demanding industry needs. As digital collections of academic materials become more available, data capture and artificial intelligence offer new possibilities for evidence-based curriculum assessment and revision. However, curriculum overhaul among tertiary institutions is generally done manually, subjectively and inconsistently resulting in content duplication, imbalance of coverage and lagged integration of new technologies. The lack of scalable analytics even makes it difficult to conduct objective cross-institutional benchmarking of curriculum. Our analysis is based on the Syllabus Corpus available on the Kaggle platform, which consists of a vast number of (human) university syllabi stored in text format. The dataset allows for a structured search of curricular contents across CS and IT programs, based on syllabus data that could be processed by machines. An AI-assisted process based on text pre-processing, TF-IDF vectorization, cosine similarity analysis and topic modelling is used to discover latent academic curriculum structures and semantic relations. The novelty of this work lies in presenting a data-driven, scalable curriculum redesign framework that goes beyond the conventional expert-centric reviews. Performance is evaluated using similarity distributions, topic coherence, and redundancy–diversity indicators. The results reveal significant syllabus overlap across courses and an imbalance between foundational and emerging technology topics, demonstrating the effectiveness of AI-based curriculum analytics for informed curriculum redesign.
Language: English
Subfield: Information Systems
Field: Computer Science
Domain: Physical Sciences
SDG: Quality education
Open Access status: hybrid
OpenAlex ID: W7203728088