The vigorous development of online education has produced massive amounts of education data. How to mine and analyze education big data has become an urgent problem in the field of education and big data knowledge engineering. As for the dynamic learning data, knowledge tracing aims to track learners’ knowledge status over time by analyzing the learners’ exercise data, so as to predict their performance in the next time step. Deep learning knowledge tracking performs well, but they mainly model the knowledge (...) components while ignoring the personalized information of questions and learners, and provide limited interpretability in the interaction between learners’ knowledge status and questions. A context-aware attentive knowledge query network model is proposed in this paper, which combines flexible neural network models with interpretable model components inspired by psychometric theory. We use the Rasch model to regularize the embedding of questions and learners’ interaction tuples, and obtain personalized representations from them. In addition, the long-term short-term memory network and monotonic attention mechanism are used to mine the contextual information of learner interaction sequences and question sequences. It can not only retain the ability to model sequences, but also use the monotonic attention mechanism with exponential decay term to extract the hidden forgetting behavior and other characteristics of learners in the learning process. Finally, the vector dot product is used to simulate the interaction between the learners’ knowledge state and questions to improve the interpretability. A series of experimental results on 4 real-world online learning datasets show that CAKQN has the best performance, and its AUC value is improved by an average of 2.945% compared with the existing optimal model. Furthermore, the CAKQN proposed in this paper can not only track learners’ knowledge status like other models but also model learners’ forgetting behavior. In the future, our research will have high application value in the realization of personalized learning strategies, teaching interventions, and resource recommendations for intelligent online education platforms. (shrink)

Social exclusion has a significant impact on cognition, emotion, and behavior. Some behavioral studies investigated how social exclusion affects pain empathy. Conclusions were inconsistent, and there is a lack of clarity in identifying which component of pain empathy is more likely to be affected. To investigate these issues, we used a Cyberball task to manipulate feelings of social exclusion. Two groups participated in the same pain empathy task while we recorded event-related potentials when participants viewed static images of body parts (...) in painful and neutral situations. The results showed early N2 differentiation between painful and neutral pictures in the central regions in both groups. The pattern at the late controlled processing stage was different. Parietal P3 amplitudes for painful pictures were significantly smaller than those for neutral pictures in the social exclusion group; they did not differ in the social inclusion group. We observed a parietal late positive potential differentiation between painful and neutral pictures in both groups. LPP amplitudes were significantly smaller in the social exclusion group than those in the social inclusion group for painful stimuli. Our results indicate that social exclusion does not affect empathic responses during the early emotional sharing stage. However, it down-regulates empathic responses at the late cognitive controlled stage, and this modulation is attenuated gradually. The current study provides neuroscientific evidence of how social exclusion dynamically influences pain empathy. (shrink)