Learning Behavior Analysis of College English Learners Based on Data Mining Technology

Abstract

Learning English is crucial as global economic integration develops since it would facilitate greater communication and collaboration with other countries. Data mining must be used in online English education given the diverse range of English learning techniques available in today's modern world. Behavior analysis has several limitations, including the possibility for simplifying or generalization that might ignore unique learning preferences or cultural quirks. In this manuscript, Learning Behavior Analysis of College English Learners Based on Data Mining Technology (LBA-CEL-DMT-DTRSRN) is proposed. Initially the data is collected from Global Language Learning Popularity Dataset. Then the data is fed into pre-processing utilizing Non-Integer Order Generalized Filters (NIOF). The NIOF is used for data cleaning. Then the pre-processed data are given to Double Transformer Residual Super-Resolution Network (DTRSRN) for predict the Error of Students Learning Behavior. In general, DTRSRN does not express adapting optimization strategies to determine optimal parameters. In order to efficiently optimize DTRSRN and precisely anticipate the error of students' learning behavior, the Multiplayer Battle Game-Inspired Optimizer (MBGIO) was developed. The proposed (LBA-CEL-DMT-DTRSRN) approach is implemented in Python. The performance of proposed method examined utilizing performance metrics like Accuracy, Precision, Recall, F1-Score and ROC. In comparison to existing methods, such as Analysis of Students’ Behavior in English Online Education Based on Data Mining (SB-EOEDM-FNN), IoT-enabled Personalized English Learning in Colleges using Big Data Analysis and Decision Support System (IOT-PELC-BDSVM), and College English Flipped Classroom Teaching Model Based on Big Data and Deep Neural Networks (CEFCT-BD-DNN), the proposed (LBA-CEL-DMT-DTRSRN) approach has 28.01%, 25.29%, and 21.05% higher accuracy, 26.35%, 21.05%, and 28.45% higher precision, and 23.78%, 26.54%, and 25.14% higher recall.