Performance prediction is a leading topic in Learning Analytics research due to its potential to impact all tiers of education. This study proposes a novel predictive modeling method to address the research gaps in existing performance prediction research. The gaps addressed include: the lack of existing research focus on performance prediction rather than identifying key performance factors; the lack of common predictors identified for both K-12 and higher education environments; and the misplaced focus on absolute engagement levels rather than relative engagement levels. Two datasets, one from higher education and the other from a K-12 online school with 13,368 students in more than 300 courses, were applied using the predictive modeling technique. The results show the newly suggested approach had higher overall accuracy and sensitivity rates than the traditional approach. In addition, two generalizable predictors were identified from instruction-intensive and discussion-intensive courses.

This study proposes two innovative approaches, the 1-channel learning image recognition (1-CLIR) and the 3-channel learning image recognition (3-CLIR) to convert student's course involvements into images for early warning predictive analysis. Multiple experiments with 5,235 students and 576 absolute/1728 relative input variables were conducted to verify their effectiveness. The results indicate both methods can significantly capture more at-risk students (the highest average recall rate is equal to 77.26%) than the following machine learning algorithms—Support Vector Machine (SVM), Random Forest (RF), and Deep Neural Network (DNN) in the middle of the semester. In addition, the innovative approaches allow minor subtypes of at-risk student identification and provide visual insights for personalized interventions. Implications and future directions are also discussed in the article.

Laboratory experience is critical to foster college students’ collaborative problem-solving (CPS) abilities, but whether students stay cognitively engaged in CPS tasks during online laboratory sessions remains unknown. This study applied multimodal data analysis to examine college students’ (N = 36) cognitive engagement in CPS during their online experimentation experience. Groups of three collaborated on CPS tasks via shared worksheets and computer-based simulations on videoconferences. Portable electroencephalogram instruments were used to determine students’ levels of cognitive engagement in CPS activities. The multimodal data analysis (e.g., electroencephalogram, surveys, and artifacts) results showed a significant difference in students’ cognitive engagement between different phases of CPS. The students’ cognitive engagement significantly differed between groups who did and did not complete the task. Additionally, intrinsic motivation predicted students’ cognitive engagement in the completion groups while self-efficacy was the primary predictor of cognitive engagement for the groups who did not complete the task.

The rapid development of learning technologies has enabled online learning paradigm to gain great popularity in both high education and K-12, which makes the prediction of student performance become one of the most popular research topics in education. However, the traditional prediction algorithms are originally designed for balanced dataset, while the educational dataset typically belongs to highly imbalanced dataset, which makes it more difficult to accurately identify the at-risk students. In order to solve this dilemma, this study proposes an integrated framework (LVAEPre) based on latent variational autoencoder (LVAE) with deep neural network (DNN) to alleviate the imbalanced distribution of educational dataset and further to provide early warning of at-risk students. Specifically, with the characteristics of educational data in mind, LVAE mainly aims to learn latent distribution of at-risk students and to generate at-risk samples for the purpose of obtaining a balanced dataset. DNN is to perform final performance prediction. Extensive experiments based on the collected K-12 dataset show that LVAEPre can effectively handle the imbalanced education dataset and provide much better and more stable prediction results than baseline methods in terms of accuracy and F1.5 score. The comparison of t-SNE visualization results further confirms the advantage of LVAE in dealing with imbalanced issue in educational dataset. Finally, through the identification of the significant predictors of LVAEPre in the experimental dataset, some suggestions for designing pedagogical interventions are put forward.

The purpose of this research was to apply multimodal learning analytics in order to systemically investigate college students’ attention states during their collaborative problem-solving (CPS) in online settings. Existing research on CPS relies on self-reported data, which limits the validity of the findings. This study looked at data in a systemic manner by collecting and analyzing multimodal data including electroencephalogram data, knowledge tests and video recordings. The study found students’ attention was positively correlated to their knowledge gains. Also, students’ attention varied across different conditions of collaborative patterns as the highest attention level was recorded in the centralized condition. A hidden Markov model was then applied to explain the difference across various conditions by identifying both the hidden states and the transitions among the states during CPS. The findings of this research advanced theoretical insights and provided practical implications on understanding and supporting CPS in online college-level courses.