Narrow Results

An instructional approach identified as a personalized learning path aims to adjust regulations to the particular interests’ necessities, talents, and skills of each pupil. Research on personalized path recommendation is critical for the development of sophisticated learning systems. The challenge emerges from the difficulty in developing personalized learning paths that properly fit every pupil’s unique characteristics and learning needs. This paper examines personalized educational routes and how deep learning (DL) algorithms can be used to construct them, with a particular emphasis on English language learning. This research proposed a novel fruit fly optimizer-tuned adjustable recurrent neural network (FFO-ARNN) to employ the students learning performance and effectively personalized English learning. For this study, gathering data on student’s demographics and English proficiency levels through assessments and educational records, in that Data on the linguistic competency of English linguistic Learners (ELLs) in grades 8–12 was collected. The data were pre-processed using tokenization for the obtained data. Term Frequency-Inverse Document Frequency (TF-IDF) is a method using extracts the feature from pre-processed data. These personalized learning approaches encourage self-directed learning and independence while increasing student engagement and academic achievement. The proposed method is implemented using Python software. In comparative analysis, the proposed method evaluates various performance metrics. The results show that the proposed method achieved superior performance in personalized learning paths in English learning. This study demonstrates how DL has the potential to revolutionize language instruction by providing customized solutions for every student.

Background: Technology integration has revolutionized traditional teaching methods in the ever-changing field of education, especially in language learning. The development of AI has created new opportunities for individualized education by allowing customized learning experiences that meet the needs of each learner.

Objective: The research aims to investigate how an AI-driven adaptive assessment and feedback system can improve English learning outcomes. This study integrates real-time feedback creation with automated essay scoring to address the problems of conventional evaluation techniques.

Methods: This research gathers a diverse student essay from various educational institutions to ensure a broad range of themes, writing styles, and skill levels. The data is clean using duplicate removal, pre-processed through text filtering and tokenization, and features extracted using Bag of $N$-Grams and Word2vec for word sequence patterns. The Seq2Seq model feedback generation algorithm aims to deliver feedback that is contextually appropriate and semantically meaningful. This study proposed a novel RO-ERNN to predict the quality of essays and improve English language learning outcomes through effective evaluation and feedback. RO optimizes model performance, which leads to more reliable assessments of students’ writing skills and provides accurate predictions of essay quality. ERNN generates meaningful feedback for students.

Results: The findings show that the Seq2Seq approach produces feedback that improves learners’ understanding of language components. The study evaluates Accuracy (98.91%), vocabulary retention rate (80%) proficiency level gain (90%), feedback accuracy (95%), $R^2$(97.780%), $F$1-score (97.50%), recall (95.40%), and precision (96.50%) demonstrating its potential to optimize language acquisition and learner performance.

Conclusion: This research has significant consequences for teachers and students, creating new opportunities for technological innovation in English language learning that are more efficient and interesting.

The rapid development of online learning platforms has transformed traditional English education by enabling flexibility, affordability, and accessibility. This study introduces an innovative English online learning platform, designed using the model–view–controller (MVC) framework — a software architectural pattern that separates the application into three interconnected components: Model (data management), view (user interface), and controller (business logic) — and a three-tier architecture. The platform integrates five core functions: user service, educational administration, online learning, platform operation management, and course recommendation. A novel English online test system was developed within this framework, featuring an intelligent recommendation engine that combines association rule-based and user-based collaborative filtering (CF) algorithms to enhance personalized learning. Comprehensive system analysis, including requirements specification, modular construction, database design, and user interface development, was conducted. Experimental evaluations demonstrate improved recommendation accuracy and system performance, offering valuable insights for optimizing English learning platforms.

The K12 educational policy stresses the importance of English as a functional language. It is anticipated that students can speak and communicate with others in English. In this study, an English class reform is designed to achieve the goal of the K12 educational policy based on the statements of learner-centered teaching, learners’ developmental difference, and learners’ adaptive development. In the refined class, group discussion, board games, and peer-evaluation are implemented for the sixth-grader students in an elementary school situated in Taiwan. Data were obtained from observation, learners’ participation, worksheet, and board games for oral practice in the classroom. The findings of this study suggest that learners’ language performances positive correspond to the refined course. In addition, learners have positive attitudes and language accuracy by linguistic board games in the class. The course reform facilitates learning through well-designed activities and leads learners toward successful learning experiences.