Wenling Li

Wenling Li

Auto-generated profile, based on publicly available information

Wenling Li

Universiti Putra Malaysia,Faculty of Educational Studies,Selangor,Malaysia

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
21 March 2024 in IEEE Access
Verified
Journal Article
Open access
DLDandan Li
Dandan Li
WLWenling Li
Wenling Li
YZYanmei Zhao
Yanmei Zhao
XLXutao Liu
Xutao Liu
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.

19 August 2022 in Plant Biotechnology Journal
Verified
Journal Article
Open access
MLMiaomiao Li
Miaomiao Li
LDLei Dong
Lei Dong
ZKZhu Keyu
Zhu Keyu
QWQiuhong Wu
Qiuhong Wu
YCYongxing Chen
Yongxing Chen
ZLZhiyong Liu
Zhiyong Liu

1 August 2022 in International Journal of Academic Research in Progressive Education and Development
Verified
Journal Article
Open access
PDF file
QHQiuyang Huang
Qiuyang Huang
MMMohd Mokhtar Muhamad
Mohd Mokhtar Muhamad
NNNur Raihan Che Nawi
Nur Raihan Che Nawi
WLWenling Li
Wenling Li
HRMARS is well established journal publisher based in Pakistan. It is publishing prominent journals in social sciences since 2011.

4 December 2023
Verified
Conference Paper
Closed access
YZYanmei Zhao
Yanmei Zhao
MMMohd Mokhtar Muhamad
Mohd Mokhtar Muhamad
SMSiti Salina Mustakim
Siti Salina Mustakim
WLWenling Li
Wenling Li
XWXuanyi Wu
Xuanyi Wu
AWAiping Wang
Aiping Wang
With the development of mobile technology, mobile-assisted language learning (MALL) is increasingly becoming a mainstream method. This study explores using a Bayesian framework to optimize learning content selection to meet learners' diverse and individual needs. The researcher briefly introduces Bayes' Theorem and explores prior and posterior selection and modeling. Considering the challenges of learner diversity and resources, the researcher also discusses how these challenges affect adaptive content selection. Based on these theoretical foundations, a Bayesian model of adaptive MALL is constructed, and the design of data processing, parameter selection, and adaptive selection algorithms are described. The effectiveness and advantages of the Bayesian framework in optimizing content selection are validated through a case study of Duolingo, a selected MALL application. The study concludes with a summary of key findings, recommendations for practical MALL applications, and directions for future research and possible challenges. Specifically, the results demonstrate that the Bayesian framework significantly enhances the adaptability and personalization of content selection in MALL, evidenced by improved learner engagement and efficiency in the case study of Duolingo. These results highlight the potential of the Bayesian approach in revolutionizing personalized learning experiences in digital platforms.

1 December 2023 in International Journal of Evaluation and Research in Education (IJERE)
Verified
Journal Article
Open access
PDF file
WLWenling Li
Wenling Li
MMMohd Mokhtar Muhamad
Mohd Mokhtar Muhamad
FFFathiyah Mohd Fakhruddin
Fathiyah Mohd Fakhruddin
WZWeili Zhou
Weili Zhou
RZRuijia Zuo
Ruijia Zuo
The purpose of this study was to express middle school teachers’ experiences of developing teacher-student relationships (TSRs) in online teaching during COVID-19 in China. The study used a qualitative phenomenological design to offer an in-depth description of the experience’s teachers perceive as strategies to develop TSRs. Participants (N=6) were from several middle schools in Nanning, GuangXi, China. Information was collected with semi-structured interviews and analyzed using a five-step phenomenological method in mental research. Data analysis revealed five general themes about teachers’ experiences. The study found that teachers’ proactively initiating dialogues, responding to student needs, emotion-based information exchange, treating students with respect, and expressing motivation and expectations for students were the strategies to develop TSRs. The results of this study can be used in middle school to create positive interventions to enhance educators’ understanding of strategies associated with TSRs.

4 December 2023
Verified
Conference Paper
Closed access
YZYanmei Zhao
Yanmei Zhao
MMMohd Mokhtar Muhamad
Mohd Mokhtar Muhamad
SMSiti Salina Mustakim
Siti Salina Mustakim
WLWenling Li
Wenling Li
XWXuanyi Wu
Xuanyi Wu
AWAiping Wang
Aiping Wang
With the popularity and development of mobile technology, mobile-assisted language learning (MALL) has gradually become essential to language learning. Intelligent recommender systems are increasingly important in MALL to improve learning efficiency and personalized experience. This paper explores how BERT (Bidirectional Encoder Representations from Transformers), a model with significant performance in natural language processing, can provide intelligent recommendations for vocabulary learning in MALL. First, it briefly introduces the basics of BERT and how it works. Then, it delves into how BERT can be utilized for data pre-processing, feature extraction, and model training in a MALL environment. In addition, this paper describes how to design an intelligent recommender system based on the user's learning history and preferences and proposes some ideas for integration with other technologies. This study suggests a new methodological framework by applying BERT technology in intelligent recommender systems within the MALL environment. Our research demonstrates how the deep learning capabilities of BERT can potentially enhance the personalized learning experience and efficiency of MALL systems. It provides a new perspective and theoretical foundation for applying deep learning technology in language learning, although further empirical research is required to validate these theoretical assumptions. Finally, an outlook on the future of BERT application in MALL and some suggestions are introduced. This paper aims to provide a reference framework for researchers and educators to understand and apply BERT in the field of MALL deeply.