This study conducted a systematic literature review of articles on learning analytics published between 2004 and January 2024. A total of 1,064 articles, identified using the keyword "learning analytic*" in the Scopus database, were analyzed. The study integrated systematic literature review and bibliometric analysis approaches to…

Research has shown that critical data literacies development for educators is seldom a core component of most campus conversations about datafication, even as extractive, datafied systems become pervasive throughout the higher education sector. This article outlines findings from an international, qualitative, Comparative Case Study (CCS) of…

This work explores how population-based engagement prediction can address cold-start at scale in large learning resource collections. The paper introduces: (1) VLE, a novel dataset that consists of content and video based features extracted from publicly available scientific video lectures coupled with implicit and explicit signals related to…

Typical data science instruction uses generic datasets like survival rates on the Titanic, which may not be motivating for students. Will introducing real-life data science problems fill this motivational deficit? To analyze this question, we contrasted learning with generic datasets and artificial problems (Phase 1) with a community-sourced…

Based on information technology to promote the upgrading of various industries, the core of Industry 4.0, the current internet big data has gradually become a hot spot of social development, and a huge amount of data gushes out. Music is the education of beauty, and it is a key to inspire people to be true and good. China has been a land of…

The unstructured multiple-attempt (MA) item response data in virtual learning environments (VLEs) are often from student-selected assessment data sets, which include missing data, single-attempt responses, multiple-attempt responses, and unknown growth ability across attempts, leading to a complex and complicated scenario for using this kind of…

The problem addressed in this study is that the potential roles of an artificial intelligence-enhanced chatbot using big data in e-learning in higher education were not widely documented in the research community. The purpose of this qualitative case study was to explore the potential roles of an artificial intelligence-enhanced chatbot using big…

This paper interrogates whether technical democracy is well-suited to contend with possible technical controversies, including the increasing prevalence of EdTech in public schooling. Drawing across Habermasian 'deliberative democracy' that seeks consensus-derived resolution, as well as more agonistic approaches that embrace conflict as the means…

Data mining approaches have been widely used to estimate student performance in online education. Various Machine Learning (ML) based data mining techniques have been developed to evaluate student performance accurately. However, they face specific issues in implementation. Hence, a novel hybrid Elman Neural with Apriori Mining (ENAM) approach was…

The COVID-19 pandemic precipitated an abrupt transition to online learning, impacting students with disabilities uniquely. This study examines the experiences of 62 such students in the new educational paradigm, employing a mixed-methods approach. Quantitative data were collected through surveys and questionnaires to assess privacy and security…

Higher education programs are rapidly transitioning online in support of a broader geographic base, working professionals, and, recently, emergency contingencies such as COVID-19. The flexibility of online courses makes them attractive to adult learners; as such, there is much academic discussion about online learning for adult learners and the…

In education, machine learning (ML), especially deep learning (DL) in recent years, has been extensively used to improve both teaching and learning. Despite the rapid advancement of ML and its application in education, a few challenges remain to be addressed. In this thesis, in particular, we focus on two such challenges: (i) data scarcity and…

Corpora, large electronic collections of texts, have been used in language teaching for several decades. Also known as Data-Driven Learning (DDL), this method has been gaining popularity because empirical research has consistently shown its effectiveness for learning. However, corpora are still underutilized, especially with learners of languages…

When writing about transformation in higher education (HE) in South Africa, it is quite popular to mention the fall of apartheid, and perhaps also 1994, as a starting point for significant change. I, myself, have made this mistake (see Bernard, 2015). However, the recent #FeesMustFall protests highlighted that many approaches to transformation…

It is widely recognized that we need to prepare students to think with data. This study investigates student interactions with digital data graphs and seeks to identify what might prompt them to shift toward using their graphs as thinking tools in the authentic activity of doing science. Drawing from video screencast data of three small groups…