This systematic review provides a comprehensive analysis of corpus-based instruction (CBI) in English as a foreign language (EFL) classroom. Corpus-based instruction is a teaching method based on actual data from natural language use, representing an important branch of corpus research. It serves as an auxiliary tool for foreign language teaching and is considered an effective instructional method. The researchers aim to thoroughly analyze the empirical studies on corpus-based instruction (CBI) in EFL classrooms, exploring research contexts, theoretical foundations, types of classroom activities, research methods, corpus tools, influencing factors, and the advantages and challenges of implementing CBI. It also proposes effective coping strategies. Following the PRISMA guidelines, the research team conducted an extensive search across four reputable databases—ScienceDirect, Google Scholar, Wiley online Library, and the Web of Science—to identify empirical studies on Data-Driven Learning (DDL) and the use of corpora in language learning contexts from 2011 to 2024. A total of forty-four studies met the inclusion criteria for the final review. This systematic review underscores CBI's effectiveness in developing various English skills and promoting learner autonomy but also identifies key challenges, such as its focus on higher-level learners, the complexity of corpus use, and instructional limitations. The review suggests solutions like comprehensive training, simplified resources and tasks, personalized learning paths, and increased resource allocation. These strategies aim to enhance the effectiveness of CBI in EFL classrooms and improve language learning outcomes.
25 July 2025 in The Asia-Pacific Education Researcher
This work aims to investigate the use of the Recurrent Neural Network (RNN) in automated English grading. In order to achieve this, this work first constructs an automated English grading system based on the Internet of Things (IoT). Next, based on the variant of RNN called Gated Recurrent Unit (GRU), it introduces a self-attention mechanism into bidirectional GRU to form the Bidirectional-GRU_self-attention (Bi-GRU_Att) model. Simultaneously, an attention pooling (AP) mechanism is introduced into bidirectional GRU to form the Bidirectional-GRU_AP (Bi-GRU_AP) model. Comparative experiments are conducted using Chinese and English corpora to compare the performance of these two models. The results indicate that the Bi-GRU_AP model performs well on both Chinese and English datasets. On the Chinese dataset, compared to Bi-GRU_Att, Bi-GRU, and GRU, its accuracy is improved by 1.3%, 9.9%, and 19%, respectively. On the English dataset, compared to Bi-GRU_Att, Bi-GRU, and GRU, its accuracy is improved by 2.2%, 9.8%, and 19.2%, respectively. This suggests that introducing the AP module enables the model to better capture sentence information, thereby enhancing model performance. Additionally, after 20 iterations, the Bi-GRU_AP model exhibits good convergence and stability. The findings provide new insights for the development of automated English subjective grading systems based on IoT and deep learning.