Desheng Yan

Digital collaborative education plays a pivotal role in digital education research and significantly contributes to enhancing teaching quality. Furthermore, it provides a new impetus for family–school–community collaboration in talent development. Nevertheless, the key drivers and predictive models of digital collaborative education remain underexplored. To address this gap, this study adopts the perspective of teachers' digital literacy, focusing on primary and secondary school teachers as research subjects. Employing machine learning methods such as gradient boosting regression trees (GBRT) and random forest, we identify the key factors influencing digital collaborative education and develop predictive models. The SHapley Additive exPlanations (SHAP) framework is applied to conduct holistic, heterogeneous, and individual‐level explanatory analyses, whereas accumulated local effects (ALE) plots are used for single‐feature explanation. The results indicate that random forest outperforms other models in predicting digital collaborative education. Digital academic assessment, digital instructional implementation, digital teaching design, and digital instructional research and innovation are the four most important feature variables in predicting the effectiveness of digital collaborative education, with digital application emerging as the strongest predictor, followed by professional development. These key features exhibit heterogeneity in predicting digital collaborative education across gender, age, educational background, and teaching experience, demonstrating nonlinear relationships. The findings provide empirical support for advancing digital collaborative education and offer valuable insights for enhancing teachers' professional development.

Objective: The parallel process latent growth curve model (PP-LGCM) was used to examine the longitudinal relationship between activities of daily living (ADL) and depression and further tested whether chronic diseases (CDs) were associated with depression via mediating variable ADL. Methods: A sample of 2014 Chinese older adults aged 60 and over from the China Health and Retirement Longitudinal Survey (CHARLS) was used. The activities of daily living scale, self-rating depression scale, and chronic diseases scale were used to investigate the ADL, depression, and CD levels of older adults. Following certain statistical analysis steps, we used SPSS 26 and Mplus 8.0 to perform statistical analysis on the data. Results: Firstly, ADL significantly declined in older adults from 2011 to 2018, while depression had a significant rise. Secondly, the intercept of ADL was correlated with the intercept of depression (r = 0.487, p < 0.001), and the slope of ADL was positively correlated with the slope of depression (r = 0.844, p < 0.001). Finally, the intercept of ADL mediated 39% of the association of chronic diseases and the intercept of depression. Conclusions: Our findings showed the trajectories of ADL and depression in older adults and demonstrated that ADL have various associations with depression in longitudinal development. In addition, the effect of chronic diseases on depression is partially mediated by ADL. The ADL play a partial mediating role between chronic diseases and depression in older adults, with an indirect effect of 39%, indicating that ADL are very important. Grasping the mediating mechanism of ADL will help alleviate depression levels in older adults with chronic diseases.

Digitalization gradually transforms digital education technology from being a teaching means to focusing on the student’s abilities. This study analyzes the data from the China Education Baseline Survey of the Renmin University of China using Coarsened Exact Matching (CEM) and quantile regression methods. The Ordinary Least Squares (OLS) regression is used to test the net effect of digital education technology on students’ academic and cognitive abilities. The OLS result shows that digital education technology has a significantly positive impact on the cognitive ability of middle school students. However, schools focusing on using digital education technology as a means of school management will lower students’ cognitive abilities. Second, the CEM method result shows a significant difference in the cognitive ability scores between students in classrooms with and without digital education technology. This indicates that digital education technology can inspire students’ internal drive, motivate them to learn, and enhance their cognitive abilities. Last, the quantile regression result shows that the use of digital education technology has heterogeneity in the development of the cognitive ability of middle school students. When the cognitive ability quantile point increases, the influence becomes more obvious, changing from not significant to significant, then to very significant. This provides some inspiration for understanding the application of digital education technology. It can be concluded that this is an effective method to study the sustainable development of cognitive abilities through heterogeneity. The method ensures individuals’ holistic and comprehensive development, thus promoting groups’ development and contributing intellectual support to them to adapt to future social requirements and lead future social development. Digital education technology endows students with the cognitive abilities for lifelong learning to solve various problems in future social life, reserve high-quality talent resources for the future, and build a learning society with extensive significance. This paper analyzes the sustainable development of students’ cognitive abilities using emerging digital education technologies. It not only deepens the understanding of sustainable development of education and humans but also provides intellectual support for society’s sustainable development.