Modeling students’ Chinese language learningpathways by introducing a behavior-driven semanticgraph construction mechanism

This study introduces an innovative approach to modeling students’ Chinese language learning pathways through abehavior-driven semantic graph construction mechanism. Traditional language learning assessment and modeling methodsoften fail to capture the nuanced and dynamic nature of language acquisition, as they overlook the significance of behavioralinteractions and contextual relationships in shaping learning outcomes. The proposed Behavior-Driven Semantic GraphModel (BDSGM) bridges this gap by integrating learners’ behavioral data such as engagement patterns, response timing, andtask completion sequences with semantic information derived from language content. Through this integration, the modelconstructs a continuously evolving graph that represents the learner’s cognitive and behavioral trajectory, enabling adaptiveinterpretation of learning progress. Complementing this model, the Behavior-Driven Semantic Graph Strategy leverages theinsights generated by BDSGM to intelligently adjust instructional pathways, recommending targeted learning materials andpersonalized practice exercises. This dual-framework approach not only facilitates a deeper understanding of individuallearning behaviors but also enhances pedagogical precision and adaptability. By aligning semantic relationships with behavioralpatterns, the methodology provides a robust foundation for data-driven personalization in language education. Ultimately, thisresearch contributes to the advancement of intelligent educational systems that promote individualized, efficient, and engagingChinese language learning experiences.Keywords: Chinese language learning, semantic graph, behavior-driven model, learning pathways, personalized education