Although informal learning with digital technology is a near universal activity among university students, the processes that influence and regulate digital informal learning (DIL) is not given. Meanwhile, digital competence is of growing importance for our current information society, and also it plays an essential role in the process of digital informal learning. However, the measurement for digital competence is a critical challenge for further understanding its development in practice. This study contributes to our understanding of students’ digital informal learning behavior by examining the effects of digital competence, along with other personal factors. Partial least square (PLS) path modeling was employed to explain the interaction and effects of these factors on students’ DIL. Students from a large-sized public university in Beijing participated in this study. The results revealed students’ personal innovativeness and digital competence are mediated by attitude to DIL to affect students’ DIL, and all these personal factors demonstrated important direct effects on students’ DIL. Additionally, significant gender differences between female and male students in certain aspects of digital competence were observed.

Learning persistence is a critical element for successful online learning. The evidence provided by psychologists and educators has shown that students’ interaction (student-student (SS) interaction, student-instructor (SI) interaction, and student-content (SC) interaction) significantly affects their learning persistence, which is also related to their academic emotions. However, few studies explore the relations among students’ interaction, academic emotions and learning persistence in online learning environments. Furthermore, no research has focused on multi-dimensional students’ interaction and specific academic emotions. Based on person-environment interaction model and transactional distance theory, this study investigates the relationship between students’ interaction and learning persistence from the perspective of moderation and mediation of academic emotions including enjoyment, boredom, and anxiety. Data were collected from 339 students who had online learning experience in China. AMOS 22.0 (IBM, Armonk, NY, USA) and SPSS 22.0 (IBM, Armonk, NY, USA) were employed to analyze the mediating and moderating effects of academic emotions, respectively. The results revealed that students’ interaction and academic emotions directly related to learning persistence. Specifically, enjoyment, anxiety and boredom had significant mediating and moderating effects on the relationship between students’ interaction and learning persistence. Based on these findings, we further discussed the theoretical and practical implications on how to facilitate students’ learning persistence in online learning environments.

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.