Large Scale Online Vocabulary Classes for prediction of College Student Learning Patterns

One of the biggest challenges for college students learning a second language is vocabulary. Despite the growing number of research projects on technology and vocabulary learning, others have shown how technology improves college students' vocabulary learning. However, authentic learning context behavioral performance pattern language is unclear. Traceability studies of college students' online vocabulary learning are rare. It emphasizes basic life learning interactions in college student learning patterns. Learning vocabulary affects classroom practice. Language teachers use idea mapping to improve reading comprehension. Analytical learning methods must also track learning processes, language use, and behavior. This study uses multimodal learning analysis to improve vocabulary and reading skills using idea mapping. Student learning pattern logs using computational tools validate college students' behavioral learning habits for data collection. Data is also analyzed using content analysis and visualization. Three college student compartmental learning subgroups have been identified and studied. The proposed VR-IMA achieves a high-performance ratio of 92.1%, learning rate of 94.2%, enhanced probability ratio of 96.6%, vocabulary rate of 95.3%, behavior rate of 91.7%, engagement rate of 93.8%, and usability level of 97.3% compared to other