Online learning has become a vital option for ensuring daily instruction in response to the emergence of the COVID-19 epidemic. However, different from conventional massive online learning, inadequate available data bring challenges for instructors to identify underachieving students in school-based online learning, which may obstruct timely guidance and impede learning performance. Exploring small-sample-supported learning performance prediction and personalized feedback methods is an urgent need to mitigate these shortcomings. Consequently, considering the problem of insufficient data, this study proposes a machine learning model for learning performance prediction with additional pre-training and fine-tuning phases, and constructs a personalized feedback generation method to improve the online learning effect. With a quasi-experiment involving 62 participants (33 in experimental group and 29 in control group), the validity of the prediction model and personalized feedback generation, and the impact of the personalized feedback on learning performance and cognitive load, were evaluated. The results revealed that the proposed model reached a relatively high level of accuracy compared to the baseline models. Additionally, the students who learned with personalized feedback performed significantly better in terms of learning performance and showed a lower cognitive load.

The goal of this study is to explore the affordances of spherical video-based virtual reality (SVVR)-based learning activities by comparing the students’ learning engagement models and their writing learning outcomes in a double-loop SVVR-based (DL-SVVR) learning activity and a single-loop SVVR-based (SL-SVVR) learning activity, respectively. For this purpose, we conduct an empirical study involving 82 fourth-grade students. The statistical results show that the students in the DL-SVVR group had higher learning behavioral engagement and better writing learning outcomes than those in the SL-SVVR group. Furthermore, as for the interrelationship between the subscales of students’ learning engagement, we find that, for the students in SL-SVVR group, their behavioral engagement can be positively predicted by the emotional engagement, while in the DL-SVVR group, students’ behavioral engagement can be positively predicted by their social engagement. For both groups, their social engagement can positively predict the emotional engagement. Importantly, our empirical results also show that the double-loop learning approach can potentially promote students’ writing learning outcomes by shifting their social engagement and behavioral engagement. The qualitative analysis results indicate that peer interaction has a positive impact on improving students’ learning interest and writing outcomes.

Research on online collaborative learning has explored various methods of collaborative improvement. Recently, learning analytics have been increasingly adopted for ascertaining learners’ states and promoting collaborative performance. However, little effort has been made to investigate the transformation of collaborative states or to consider cognitive load as an essential factor for collaborative intervention. By bridging collaborative cognitive load theory and system dynamics modeling methods, this paper revealed the transformation of online learners’ collaborative states through data analysis, and then proposed an optimized mechanism to ameliorate online collaboration. A quasi-experiment was conducted with 91 college students to examine the potential of the optimized mechanism in collaborative state transformation, awareness of collaboration, learning achievement, and cognitive load. The promising results demonstrated that students learning with the optimized mechanism performed significantly differently in collaboration and knowledge acquisition, and no additional burden in cognitive load was noted.