College transfer students are those who follow a different trajectory in their higher education journeys than traditional students, completing a sub-degree before pursuing a bachelor’s degree at a university. While the possibility of transferring makes higher education accessible to these students, previous studies have found that they face various challenges, from issues with course load to language challenges. This study aims to examine (1) the critical factors contributing to the success of transfer students in a language course; and (2) how transfer students perform better or worse than those who enter university directly. This study conducted learning analytics with 700 college transfer students in Hong Kong, retrieving their demographic and learning data from the learning management system and the university academic registry. The results suggest that English exam scores, current semester GPA, graduating GPA at community college and current course load are important predictors of transfer students’ success in language courses. This study also finds that transfer students have lower levels of language proficiency than direct entrants. It concludes with specific recommendations to make higher education more accessible to transfer students and suggestions on how to use learning analytics to track students with different trajectories. © The Author(s) 2023.

College transfer students are those who follow a different trajectory in their higher education journeys than traditional students, completing a sub-degree before pursuing a bachelor's degree at a university. While the possibility of transferring makes higher education accessible to these students, previous studies have found that they face various challenges, from issues with course load to language challenges. This study aims to examine (1) the critical factors contributing to the success of transfer students in a language course; and (2) how transfer students perform better or worse than those who enter university directly. This study conducted learning analytics with 700 college transfer students in Hong Kong, retrieving their demographic and learning data from the learning management system and the university academic registry. The results suggest that English exam scores, current semester GPA, graduating GPA at community college and current course load are important predictors of transfer students' success in language courses. This study also finds that transfer students have lower levels of language proficiency than direct entrants. It concludes with specific recommendations to make higher education more accessible to transfer students and suggestions on how to use learning analytics to track students with different trajectories. Copyright © 2023 Springer.

Purpose: This study aims to examine the impact of the transformation of an assessment on students' performance and perspectives in an English for Academic Purposes course in Hong Kong. The assessment was changed from the traditional pen-and-paper mode to an unproctored online mode. Design/methodology/approach: Using mixed methods, the research team analysed the differences between the assessment performances of those who took the course before the pandemic (n = 664) and those who took it during the pandemic (n = 702). Furthermore, focus group interviews were conducted with seven students regarding their perspectives on the unproctored assessment. Findings: The results revealed that, although there were no major differences in the overall grades of the two groups, students who were assessed online during the pandemic performed significantly better in terms of their English use. Nevertheless, the shift to online assessment had several negative effects on the students. Originality/value: Previous studies on unproctored online assessments (UOA) were concerned with potential learning quality issues, such as plagiarism and grade inflation. This study, however, provided empirical evidence that high-quality assessment delivery can be provided via UOA if the question types and assessment arrangements are carefully decided. Copyright © 2023 Emerald.

This study investigated how English learners complete multimodal formative quizzes. Participants included 17,950 students enrolled in a mandatory English for Academic Purposes course at a university in Hong Kong. We retrieved data from Blackboard, a learning management system, and conducted a two-step cluster analysis to examine student self-regulated learning (SRL) profiles with the quizzes. We first identified five clusters of learners with distinctively different self-regulated learning patterns. Then, we performed a multivariate analysis of variance (MANOVA) to further explore their differences in SRL, in terms of start day, days started before deadline, differences in scores between first and last attempt, and scores in language learning activities. Our findings echoed those of previous studies on the relationship between self-regulated learning and academic success. This research enables us to better understand the needs of EAP students in Hong Kong. Copyright © 2023 International Forum of Educational Technology & Society.

This study investigates how the online behaviors of students can be associated with student outcomes via a learning analytics approach. The objective of this study is to examine whether online behaviors of students can predict student success in an English course. Also, this study aims to examine whether some machine learning techniques performed better than others. Learners in this study were students in an English for Academic Purposes course at a university in Hong Kong. Other than face-to-face teaching, this course included a mandatory multimodal language learning package first introduced in 2012. The research team retrieved a mega-dataset from all learners who took the course from 2012 to 2019 (n = 17,968). Using the Classification Tree technique, Logistical Regression, and Artificial Neural Networks, the research team derived three predictive algorithms to associate various online engagement variables (e.g., start day, first attempt scores, and number of attempts) with course success. Results suggest that Classification Tree performed better in predictive accuracy and F1 ratio. The chapter provides useful insights for adaptive design. The study also discusses several useful suggestions on how practitioners can adopt these algorithms for better adaptive design. Copyright © 2024 selection and editorial matter, Patsy D. Moskal, Charles D. Dziuban, and Anthony G. Picciano; individual chapters, the contributors.

Blended learning pedagogical practices supported by learning management systems have become an important part of higher education curricula. In most cases, these blended curricula are evaluated through multimodal formative assessments. Although assessments can strongly affect student outcomes, research on the topic is limited. In this paper, we adopted a learning analytics approach to explore student engagement with formative assessments and the power of these assessments to predict student outcomes in an English for Academic Purposes courses in a Hong Kong university. The study retrieved the data logs from 7,815 students and used the data to analyze student engagement with the formative assessments. The results suggested that the students put effort into completing the assessments. The degree to which assessments predict learning outcomes depend on students’ level of subject knowledge and their understanding of the relevance of the assessments. This study showed that learning analytics provided reliable evidence for understanding students’ engagement and identifying at-risk students. Therefore, learning analytics research has the potential to inform pedagogical practice. Copyright © 2022 The Author(s).

In recent years, research using learning analytics to predict learning outcomes has begun to increase. This emerging field of research advocates the use of readily-available data to inform teaching and learning. The current case study adopts a learning analytics approach to evaluate the online learning package of an academic English course in a university in Hong Kong. This study aims to (1) explore the completion pattern of use of the online learning package by students in a generic undergraduate academic skills course; and (2) predict student outcomes based on their online behaviour patterns. Over three academic years, the study examined usage logs for 7000+ students that were available on the university's learning management system. Student assessment component scores, online activity completion rates, and online behavioural patterns were identified and examined using descriptive analysis, bivariate correlation analysis, and multiple regression analysis. The findings reveal insights into different online learning behavioural patterns that would benefit blended course designers. For instance, some students started using the online learning package early in the semester but fulfilled only the minimum required online work, whereas others greatly exceeded the basic requirement and continued doing activities in the online package even after the semester had finished. The relationship between learning activities in the online package and assessment component grades was found to be weak but meaningful. A regression model was developed drawing on the completion rates to predict overall student scores, and this model successfully identified several specific factors, such as total number of attempts and performance in individual online learning activities, as predictors of the final course grade.
[Copyright of Electronic Journal of e-Learning is the property of Academic Conferences and Publishing International Ltd.]

This paper reports and discusses the results of a study aimed at automatically categorising teacher feedback on student writing. A total of 3412 teachers’ written comments on 90 students’ draft essays were collected from an EFL course offered by a Hong Kong university during the first semester of 2016/17. The data were primarily used to design and implement an automated tool to classify teachers’ comments with respect to a taxonomy of their characteristics. The findings of this study show that the performance of the automated tool is comparable to that of human annotators, suggesting the feasibility of using the automatic approach to identify and analyse different types of teacher feedback. This study can contribute to future research into the investigation of the impact of teacher feedback on student writing in a big data world. Copyright © 2018 International Journal of Information and Education Technology. All rights reserved.