Textual data, as a key carrier of learning feedback, is continuously produced by many students within course forums. The temporal nature of discussion requires students’ emotions and concerned aspects (e.g. teaching styles, learning activities, etc.) to be dynamically tracked for understanding learning requirements. To characterize dynamics of emotion-aspects, this paper presents an unsupervised model, namely temporal emotion-aspect model (TEAM), modeling time jointly with emotions and aspects to capture emotion-aspect evolutions over time. Especially, the primary output of TEAM is two-fold: emotion-specific aspect probabilistic distributions and their evolutions over time. With the discussion data from two online course forums, we validated the performance of TEAM and utilized this model to discover most concerned emotion-aspects as well as their evolutionary trends for the whole learning group and different achievement levels of groups, respectively. The results indicated that, (1) content-related aspects were the main focus with higher probabilities to negative and confused emotions; (2) there were higher probabilities of emotional expressions in the initial and final stages of a semester; (3) compared with high- and medium-achieving students, low-achieving students were less active in emotional engagement on the whole, and tended to express more confusion in the final stage of a semester.

Digital data trails from disparate sources covering different aspects of student life are stored daily in most modern university campuses. However, it remains challenging to (i) combine these data to obtain a holistic view of a student, (ii) use these data to accurately predict academic performance, and (iii) use such predictions to promote positive student engagement with the university. To initially alleviate this problem, in this paper, a model named Augmented Education (AugmentED) is proposed. In our study, (1) first, an experiment is conducted based on a real-world campus dataset of college students (N = 156) that aggregates multisource behavioral data covering not only online and offline learning but also behaviors inside and outside of the classroom. Specifically, to gain in-depth insight into the features leading to excellent or poor performance, metrics measuring the linear and nonlinear behavioral changes (e.g., regularity and stability) of campus lifestyles are estimated; furthermore, features representing dynamic changes in temporal lifestyle patterns are extracted by the means of long short-term memory (LSTM). (2) Second, machine learning-based classification algorithms are developed to predict academic performance. (3) Finally, visualized feedback enabling students (especially at-risk students) to potentially optimize their interactions with the university and achieve a study-life balance is designed. The experiments show that the AugmentED model can predict students’ academic performance with high accuracy.

The application of information and communications technology (ICT) in higher educational institutions has led to the transformation of the environment from digital to smart. The assessment of smart learning environments will highlight the advantages and disadvantages of its construction results and help establish a sustainable space for students’ personalized study. However, the construction level and application effect are difficult to judge thoroughly, so a comprehensive evaluation method is needed. By rethinking the structure of a smart learning environment (the physical space, resource space and social space), this paper uses analytic hierarchy process–fuzzy comprehensive evaluation (AHP-FCE) and genetic algorithm–back propagation (GA-BP) neural network algorithm methods to assess the environment, with the aim of determining their scope of application and providing suggestions for updating the environment construction process. The questionnaire results of 300 students at Central China Normal University (CCNU) were analyzed with an evaluation index system that was collected by expert scoring. The results showed that the AHP-FCE model can simultaneously obtain multiple results but can be influenced by subjective factors, whereas the GA-BP-based model can make the evaluation process easier and improve fault tolerance. The results also indicated that the classrooms need to be modified in terms of the perception infrastructure and resource modules to provide students with a more suitable and comfortable learning space. We hope the study can provide a reference and inspiration for the construction and assessment of smart learning environments.

Known as the third revolution of information technology, the Internet of Things (IoT) embodies the transformation of human technology from “virtual” to “reality”. The application of IoT in education has risen the concerns of both researchers and practitioners. However, there are few research on using bibliometric to visually analyze the hotspots and trends of the IoT in education. In this study, a total of 2257 articles, including (1) 1243 domestic articles from 2005 to 2021; (2) 1014 foreign articles from 2005 to 2021, were collected for comparative analysis between China and foreign countries using the visualization software CiteSpace. The results show that authoritative journals both at home and abroad have paid varying degrees of attentions to the basic theories, emerging technologies and applications of IoT in education. The number of research literatures on this topic is generally increasing year by year. It is particularly worth mentioning that in the field of the IoT in education, on the one hand, the United States, China and Spain are the top three major countries actively participate in, and their international academic cooperation is relatively close; on the other hand, the main research findings are concentrated in the northern and eastern hemispheres, while there is less distributed in the southern and western hemispheres. Regrading research directions, on the whole, much attention has been paid to the construction of smart learning environment; to be specific, its research focus has shifted to the deep integration of intelligent technology and education (e.g., learning feedback supported by IoT technology is delivered to student with the purpose of improving teaching effect). However, in general, the application of IoT in education is still in its infancy, and the scope of practical application is relatively limited. Therefore, future research will concentrate on construction of smart education environment, curriculum teaching and data-driven education evaluation, in order to inaugurate a new situation capable of carrying out experimental teaching, presenting abstract concepts and connecting realistic situations.

As a sub-challenge of EmotiW (the Emotion Recognition in the Wild challenge), how to improve performance on the AFEW (Acted Facial Expressions in the wild) dataset is a popular benchmark for emotion recognition tasks with various constraints, including uneven illumination, head deflection, and facial posture. In this paper, we propose a convenient facial expression recognition cascade network comprising spatial feature extraction, hybrid attention, and temporal feature extraction. First, in a video sequence, faces in each frame are detected, and the corresponding face ROI (range of interest) is extracted to obtain the face images. Then, the face images in each frame are aligned based on the position information of the facial feature points in the images. Second, the aligned face images are input to the residual neural network to extract the spatial features of facial expressions corresponding to the face images. The spatial features are input to the hybrid attention module to obtain the fusion features of facial expressions. Finally, the fusion features are input in the gate control loop unit to extract the temporal features of facial expressions. The temporal features are input to the fully connected layer to classify and recognize facial expressions. Experiments using the CK+ (the extended Cohn Kanade), Oulu-CASIA (Institute of Automation, Chinese Academy of Sciences) and AFEW datasets obtained recognition accuracy rates of 98.46%, 87.31%, and 53.44%, respectively. This demonstrated that the proposed method achieves not only competitive performance comparable to state-of-the-art methods but also greater than 2% performance improvement on the AFEW dataset, proving the significant outperformance of facial expression recognition in the natural environment.

Human emotions are complex psychological and physiological responses to external stimuli. Correctly identifying and providing feedback on emotions is an important goal in human–computer interaction research. Compared to facial expressions, speech, or other physiological signals, using electroencephalogram (EEG) signals for the task of emotion recognition has advantages in terms of authenticity, objectivity, and high reliability; thus, it is attracting increasing attention from researchers. However, the current methods have significant room for improvement in terms of the combination of information exchange between different brain regions and time–frequency feature extraction. Therefore, this paper proposes an EEG emotion recognition network, namely, self-organized graph pesudo-3D convolution (SOGPCN), based on attention and spatiotemporal convolution. Unlike previous methods that directly construct graph structures for brain channels, the proposed SOGPCN method considers that the spatial relationships between electrodes in each frequency band differ. First, a self-organizing map is constructed for each channel in each frequency band to obtain the 10 most relevant channels to the current channel, and graph convolution is employed to capture the spatial relationships between all channels in the self-organizing map constructed for each channel in each frequency band. Then, pseudo-three-dimensional convolution combined with partial dot product attention is implemented to extract the temporal features of the EEG sequence. Finally, LSTM is employed to learn the contextual information between adjacent time-series data. Subject-dependent and subject-independent experiments are conducted on the SEED dataset to evaluate the performance of the proposed SOGPCN method, which achieves recognition accuracies of 95.26% and 94.22%, respectively, indicating that the proposed method outperforms several baseline methods.