Research Article
Kiran Fahd, Shah J. Miah
CONT ED TECHNOLOGY, Volume 17, Issue 4, Article No: ep606
ABSTRACT
The increasing reliance on the learning management system (LMS) in this era of digital education offers a vital source of student data that can be leveraged to predict student academic progress. Predicting student academic progress in higher education (HE) supports timely intervention and enhances student retention. This study develops and compares multiple machine learning (ML) and deep learning (DL) models to identify at-risk students based on students’ interaction data with LMS by leveraging an integrated DSR methodology. Multiple predictive models are developed by incorporating data augmentation and balancing techniques to address class imbalance and enhance the accuracy of the predictive model. The study compares ten different models to achieve the highest classification accuracy in predicting students at risk of failing through the integration of through the integration of both ML and DL algorithms, including random forest, decision tree, convolutional neural networks, multi-layer perceptron, and long short-term memory (LSTM). The comparison results unscored the value of the DL based predictive model in the HE setting to precisely predict student academic performance, particularly the LTSM based model, which has the highest and nearly perfect accuracy. The existing LMS systems can incorporate this DL based predictive model to provide educational stakeholders with benefits and insights that support students’ academic journeys and institutional success.
Keywords: machine learning, deep learning, design research, higher education, LMS data, student academic progress
Research Article
Rongrong Huang, Nagaletchimee Annamalai
CONT ED TECHNOLOGY, Volume 16, Issue 4, Article No: ep537
ABSTRACT
To equip students with 21st century skills to be competent global citizens and succeed academically and professionally, information and communication technology tools are being utilized to facilitate deep learning in higher education. This study integrated a small private online course (SPOC) with face-to-face (F2F) classroom learning to design and implement a blended English as a foreign language (EFL) course for deep learning. A mixed-method design was employed to investigate the learning experiences and perceptions of EFL students in the SPOC-based blended learning (BL) environment. The primary objective was to examine whether and how the teaching, social and cognitive presences were established from the perspective of the community of inquiry (CoI) model. Participants were 60 students enrolled in an eight-week English communicative course in a Chinese college. Quantitative data was obtained from the CoI and BL surveys, while qualitative data was gathered through individual interviews with 10 students. The results showed that a CoI was established, and deep learning happened in both SPOC and F2F learning areas with a more salient teaching presence in the SPOC area, a stronger social presence and a higher frequency of resolution phase reached in the F2F area. Furthermore, learners expressed satisfaction with the BL course, perceiving it as effective for English language acquisition. Pedagogical implications were offered to assist educators and institutions in optimizing the use of SPOC-based BL to enhance deep learning.
Keywords: SPOC, deep learning, blended learning, EFL learning, community of inquiry