MULTIMODAL LEARNING ANALYTICS FOR EARLY DETECTION AND PERSONALIZED INTERVENTION OF STUDENT LEARNING DIFFICULTIES
Early identification of student learning difficulties is important because academic disengagement, weak assessment performance, irregular participation, and delayed help-seeking may become visible before final failure or withdrawal. Conventional learning analytics systems often rely on a single data source, limiting their ability to represent the multidimensional nature of learning. This paper proposes a multimodal learning analytics framework that combines academic records, assessment performance, virtual learning environment (VLE) interactions, temporal engagement patterns, and textual or behavioral indicators to estimate student learningrisk profiles at an early stage. The framework uses modality-specific preprocessing, feature alignment, multimodal fusion, supervised prediction, explainability, and a rule-guided personalized intervention layer. OULAD is selected as the primary reproducible dataset because it links student demographics, assessment results, registration information, and VLE interaction logs. The proposed design is motivated by recent research showing the value of multimodal fusion and the need to connect risk prediction with actionable interventions. A prototype evaluation is included to demonstrate the intended analysis workflow and visualization; the numerical prototype results are explicitly illustrative and must be replaced by measured results after executing the pipeline on the downloaded OULAD data. The paper contributes an end-toend architecture, feature-engineering strategy, risk classification scheme, intervention mapping, evaluation protocol, and an ethics-aware deployment model for early academic support.
Authors
- Abigail Grace (ORCID: https://orcid.org/0000-0002-9976-6297)
- Dr .K. Nirmala
Publication Details
- Journal
- INTERNATIONAL JOURNAL OF HUMANITIES AND LEARNING TECHNOLOGY INNOVATION (IJHLT)
- Published
- 2026-11-18
- DOI
- https://doi.org/10.65725/ijhlt/1/3/010
- Primary Topic
- Online Learning and Analytics
- Type
- article
- Field-Weighted Citation Impact
- 0.00