Teacher emotion recognition (TER) has a significant impact on student engagement, classroom atmosphere, and teaching quality, which is a research hotspot in the smart education area. However, existing studies lack high-quality multimodal datasets and neglect common and discriminative features of multimodal data in emotion expression. To address these challenges, this research constructs a multimodal TER dataset suitable for real classroom teaching scenarios. TER dataset contains a total of 102 lessons and 2,170 video segments from multiple educational stages and subjects, innovatively labelled with emotional tags that characterize teacher‒student interactions, such as satisfaction and questions. To explore the characteristics of multimodal data in emotion expression, this research proposes an emotion dual-space network (EDSN) that establishes an emotion commonality space construction (ECSC) module and an emotion discrimination space construction (EDSC) module. Specifically, the EDSN utilizes central moment differences to measure the similarity to assess the correlation between multiple modalities within the emotion commonality space. On this basis, the gradient reversal layer and orthogonal projection are further utilized to construct the EDSC to extract unique emotional information and remove redundant information from each modality. Experimental results demonstrate that the EDSN achieves an accuracy of 0.770 and a weighted F1 score of 0.769 on the TER dataset, outperforming other comparative models.

When incorporating new technology into medical curricula, it is essential to evaluate student success and resource preference. Our team created a database of virtual 3D scanned prosections for students to use while studying Gross Anatomy. Incoming first year medical students were recruited to take part in a study examining the effectiveness and preference for this resource. The study was conducted in four parts: first, a pre-test using physical prosections and images of virtual 3D scans of prosections; second, a teaching session using physical prosections or virtual 3D scans of prosections; third, a post-test identical to the pre-test; forth, a post-test survey. Twenty-nine students participated in this study (physical prosection teaching group [physical]= 15; virtual 3D scans teaching group [virtual] = 14). Exam scores significantly increased in both groups regardless of past anatomy experience with no significance found between groups (physical = 42.6% ± 17.9%; virtual = 44.3% ± 24.0%; P < 0.01). Students taught using the virtual 3D scans were more likely to agree that they “would be able to sufficiently learn anatomy using 3D scans” (physical = 3.0 ± 0.8; virtual = 4.1 ± 1.1; P < 0.01). Regardless of teaching group, students disagreed that they “would have a similar lab experience if they learned 3D scans instead of dissection” (physical = 2.1 ± 0.6; virtual = 2.5 ± 0.8), but agreed that they would use the virtual 3D scans to prepare for the dissection lab and practical/written exam (physical = 4.5 ± 0.8; virtual = 4.9 ± 0.3). This study demonstrates that virtual 3D scans are comparable to physical prosections in anatomy learning, but students do not support this resource replacing the dissection process.

In the era of digital transformation, the integration of intellectual property (IP) education with curriculum-based ideological and political education has become a core focus of professional degree education. Taking IP education as the starting point, this paper puts forward an ideological and political path of curriculum concentrating on lifelong learning, practice-driven learning, and international perspective. The curriculum is committed to cultivating high-quality talents with the consciousness of the rule of law, innovation ability, and social responsibility. In response to challenges such as the lack of diverse content, weak integration of practice, and limited international vision in the current IP teaching, this paper innovatively proposes using AI to optimize the teaching mode, build an intelligent and personalized learning platform, and promote the coordinated development of IP education and curriculum-based ideological and political education. The findings of this research suggest that the integration of professional IP education with ideological and political education not only improves teaching quality but also enhances students’ social responsibility and practical ability, which is significant for promoting the overall development of IP education. The paper provides both theoretical foundation and practical guidance for professional degree education in the new era.

As the driving force of global educational transformation, digital education functions as a pragmatic vehicle for technology-driven innovation and a strategic path for advancing educational equity and fostering high-quality development. The Ministry of Education of the People’s Republic of China (2024) issued the Shanghai call for cooperation on digital education, which underscored the imperative to ensure that digital education benefited everyone fairly and collaboratively advanced the United Nations’ 2030 sustainable development goals. Reshaping the educational ecosystem through digital transformation, deepening the integration of teaching and AI technologies, and building an open, inclusive, and intelligent learning system have increasingly become a global consensus.

In response to this global imperative, Frontiers of Digital Education has consistently been tracking and reflecting international development in this field. Aiming to capture the forefront of international academic discourse and innovation, the journal launched a pioneering research project titled Digital Education Fronts 2025. This project aspires to provide intellectual leadership, contribute to the construction of a global digital education discourse, and promote practical innovation in this field.

The project was spearheaded by the journal’s editorial office in collaboration with Clarivate and supported by a multidisciplinary research team. Utilizing a dataset of nearly 60,000 academic papers on digital education published worldwide from 2019 to 2024, the team conducted a comprehensive scientometric analysis using Clarivate’s advanced analytical tools, combined with in-depth exploration by educational technology scholars. This process identified 66 significant thematic clusters, which were further refined through multiple rounds of expert review by a cross-disciplinary panel of scholars specializing in education, AI, and library and information science, ultimately resulting in the selection of the top 10 critical fronts presented in this report.

This report consists of 3 main sections: Section 1 outlines the research framework, including the methodologies for data integration, the mechanisms of cross-institutional collaboration, and the procedures for topic selection; Section 2 provides a global research landscape in digital education; Section 3 focuses on the top 10 critical fronts and offers detailed insights supported by empirical cases and trend forecasting. These are interpreted through multiple perspectives, including technological iteration, policy coordination, and emergent ethical challenges. This report encapsulates a midterm analysis of global advancements in digital education and offers a forward-looking analysis of cutting-edge technologies, such as generative AI and immersive learning environments, as well as their applications in education. It serves as a strategic reference for educational digitalization over the next 5 to 10 years.

The identification, interpretation, and projection of research hotspots in digital education depend on coordinated innovation. Through this project, the editorial team has advanced the journal’s mission to foster high-impact academic publishing, develop a specialized international academic platform, and refine its institutional infrastructure. It extends its heartfelt appreciation to all collaborating institutions and scholars, both domestic and foreign, for their invaluable contributions to this project.