JERAJournal of Electronic Research and Application2208-35022208-3510Bio-Byword Scientific Publishing Pty. Ltd.10.26689/jera.v9i2.10085ArticleResearch on Constructing Personalized Learner Profiles Based on Multi-Feature Fusionhttps://artdesignp.com/journal/JERA/9/2/10.26689/jera.v9i2.10085PanXing,LuMeixiu2025922025-04-03This study proposes a learner profile framework based on multi-feature fusion, aiming to enhance the precision of personalized learning recommendations by integrating learners’ static attributes (e.g., demographic data and historical academic performance) with dynamic behavioral patterns (e.g., real-time interactions and evolving interests over time). The research employs Term Frequency-Inverse Document Frequency (TF-IDF) for semantic feature extraction, integrates the Analytic Hierarchy Process (AHP) for feature weighting, and introduces a time decay function inspired by Newton’s law of cooling to dynamically model changes in learners’ interests. Empirical results demonstrate that this framework effectively captures the dynamic evolution of learners’ behaviors and provides context-aware learning resource recommendations. The study introduces a novel paradigm for learner modeling in educational technology, combining methodological innovation with a scalable technical architecture, thereby laying a foundation for the development of adaptive learning systems.

Xiao J, Qiao H, Li X, 2019, Construction and Empirical Study of Online Learner Profiles in Big Data Environments. Open Education Research, 25(4): 110–120.

Wang L, Guo W, Yang H, 2021, Research on Personalized Course Recommendations Using Learner Profiles. China Academic Journal Electronic Publishing House, (12): 55–62.

Schroeder N, Yang F, Banerjee T, et al., 2018, The Influence of Learners’ Perceptions of Virtual Humans on Learning Transfer. Computers & Education, 126: 170–182.

Piech C, Spencer J, Huang J, et al., 2015, Deep Knowledge Tracing. Computer Science, 3(3): 19–23.

Zhang J, Zhang Y, Zou Q, et al., 2018, What Learning Analytics Tells Us: Group Behavior Analysis and Individual Learning Diagnosis Based on Long-term and Large-scale Data. Educational Technology and Society, (1): 245–258.

Shao Y, Qin Y, Cui Y, et al., 2024, User Profile Generation Method based on Multi-granularity Information Fusion. Journal of Computer Applications, 41(2): 401–407.

Ban Q, Wu W, Hu W, et al., 2022, Personalized Course Recommendations Based on a Learner’s Knowledge and Personality. Journal of East China Normal University (Natural Science), (6): 87–100.

Wang L, Guo W, YANG H, 2021, Study on Realizing Personalized Course Recommendation by Using Learner Portraits. China Academic Journal Electronic Publishing House, (12): 55–62.

Chen D, Chen Z, 2023, Hierarchical Description-aware Personalized Recommendation System. Journal of East China Normal University (Natural Science), 6: 73–84.

Zhong Y, Xue H, 2024, Design and Implementation of Student Portrait Personalized Recommendation System Based on Deep Hash Algorithm. Journal of the Hebei Academy of Sciences, 41(1): 40–45.