The Impact of Mobile Interactive Technology on International Chinese Learning: A Case Study of AI-Driven Applications

Abstract

With the rapid advancement of mobile internet technology and artificial intelligence (AI), mobile interactive technology has been increasingly applied to international Chinese learning. By leveraging smart devices and online platforms, learners can overcome the limitations of traditional classroom teaching, enabling more flexible and personalized learning experiences. However, existing research has yet to fully consider key factors such as individual learner differences, interaction dynamics, and learning behavior prediction in assessing the effectiveness of mobile interactive learning for Chinese language acquisition. Consequently, enhancing learning outcomes and prediction accuracy through advanced AI-driven approaches has become a critical issue in the field of Chinese language education. Most current studies focus on specific tools or teaching models, often relying on localized data analysis while lacking a comprehensive exploration of learner behavior dynamics, individual preferences, and interaction patterns. To address this gap, this study proposes a predictive model for mobile interactive learning among international Chinese learners, integrating a hypergraph attention mechanism (HGAM) and a graph convolutional network (GCN). By modeling learner interactions, behavioral characteristics, and preferences, this study aims to improve the accuracy of learning outcome predictions and provide theoretical foundations for personalized and intelligent teaching strategies. The novelty of this study lies in its pioneering integration of graph neural networks with mobile interactive learning, surpassing the limitations of traditional teaching models and contributing valuable insights to both academic research and practical applications.