Learning is a multimodal process, and learning analytics (LA) researchers can readily access rich learning process data from multiple modalities, including audio-video recordings or transcripts of in-person interactions; logfiles and messages from online activities; and biometric measurements such as eye-tracking, movement, and galvanic skin…

Predicting student performance using educational data is a significant area of machine learning research. However, class imbalance in datasets and the challenge of developing interpretable models can hinder accuracy. This study compares different variations of the Synthetic Minority Oversampling Technique (SMOTE) combined with classification…

Central to the institutionalization of learning analytics is the need to understand and improve student learning. Frameworks guiding the implementation of learning analytics flow from and perpetuate specific understandings of learning. Crucially, they also provide insights into how learning analytics acknowledges and positions itself as entangled…

In modeling missing data, the missing data latent variable of the confirmatory factor model accounts for systematic variation associated with missing data so that replacement of what is missing is not required. This study aimed at extending the modeling missing data approach to tetrachoric correlations as input and at exploring the consequences of…

Purpose: This paper aims to consider ways to visually model data generated by qualitative case studies, pointing out a need for visualizations that depict both synchronic relations across representations and how those relations change diachronically. To develop an appropriate modeling approach, the paper critically examines Max Boisot's I-Space…

Purpose: While designing personally meaningful activities with data technologies can support the development of data literacies, this paper aims to focuses on the overlooked aspect of how learners navigate tensions between personal experiences and data trends. Design/methodology/approach: The authors report on an analysis of three student cases…

Data pooling is a powerful strategy in empirical research. However, combining multiple datasets often results in a large amount of missing data, as variables that are not present in some datasets effectively contain missing values for all participants in those datasets. Furthermore, data pooling typically leads to a mix of continuous and…

Relying on the nation's first judicial big data research base for people's courts in Southeast University, Southeast University Law School has set up a training direction for graduate students in legal big data and artificial intelligence, and explored the "three-dimensional, small-scale, wide-ranging, and large-scale ecology." The…

Feedback on how students progress through completing subgoals can improve students' learning and motivation in programming. Detecting subgoal completion is a challenging task, and most learning environments do so either with "expert-authored" models or with "data-driven" models. Both models have advantages that are…

Grounded within current reform recommendations and built upon Giere's views (1986, 1999) on model-based science, we propose an alternative approach to science education which we refer to as the "Evidence-Explanation (EE) Continuum." The approach addresses conceptual, epistemological, and social domains of knowledge, and places emphasis…

Data-informed decision-making in teachers' practice, now recommended by different teacher inquiry models and policy documents, implies deep practice change for many teachers. However, not much is known about how teachers perceive the different steps that analytics-informed teacher inquiry entails. This paper presents the results of a study into…

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…

Multilevel factor mixture modeling (FMM) is a hybrid of multilevel confirmatory factor analysis (CFA) and multilevel latent class analysis (LCA). It allows researchers to examine population heterogeneity at the within level, between level, or both levels. This tutorial focuses on explicating the model specification of multilevel FMM that considers…

Large-scale data and data visualizations are ubiquitous now in the stories that shape our society. In particular, these stories influence youth and families' communication and understanding of scientific, social, and personal issues. Consequently, we need to better understand how youth and families can engage and learn with the tools that generate…

The development of new statistical models for the meta-analysis of diagnostic test accuracy studies is still an ongoing field of research, especially with respect to summary receiver operating characteristic (ROC) curves. In the recently published updated version of the "Cochrane Handbook for Systematic Reviews of Diagnostic Test…