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.

Identifying the epistemic emotions of learner-generated reviews in massive open online courses (MOOCs) can help instructors provide adaptive guidance and interventions for learners. The epistemic emotion identification task is a fine-grained identification task that contains multiple categories of emotions arising during the learning process. Previous studies only consider emotional or semantic information within the review texts alone, which leads to insufficient feature representation. In addition, some categories of epistemic emotions are ambiguously distributed in feature space, making them hard to be distinguished. In this article, we present an emotion-semantic-aware dual contrastive learning (ES-DCL) approach to tackle these issues. In order to learn sufficient feature representation, implicit semantic features and human-interpretable emotional features are, respectively, extracted from two different views to form complementary emotional-semantic features. On this basis, by leveraging the experience of domain experts and the input emotional-semantic features, two types of contrastive losses (label contrastive loss and feature contrastive loss) are formulated. They are designed to train the discriminative distribution of emotional-semantic features in the sample space and to solve the anisotropy problem between different categories of epistemic emotions. The proposed ES-DCL is compared with 11 other baseline models on four different disciplinary MOOCs review datasets. Extensive experimental results show that our approach improves the performance of epistemic emotion identification, and significantly outperforms state-of-the-art deep learning-based methods in learning more discriminative sentence representations.

Personalized e-learning systems are applications of consumer electronics in the field of education that provide individualized and adaptive services for users. Knowledge tracing (KT), as a key technology, aims to model learners’ knowledge states through the interactions between learners and learning resources, and predicts their future performance. However, the problem of interaction sparsity in educational resources leads to the fact that simple representations of questions usually fail to accurately capture students’ knowledge states. In this paper, inspired by the data-driven paradigm, we propose a novel knowledge tracing method named weighted heterogeneous graph-based Three-view Contrastive Learning framework for Knowledge Tracing (TCL4KT). Technically, three different view encoders in TCL4KT complement each other to obtain question embeddings with rich information. Specifically, TCL4KT considers the semantic information of higher-order, heterogeneous and the downstream task on a weighted heterogeneous graph of KT to learn high-quality representations. Besides, a meta-path-based positive sample selection strategy and joint contrastive loss are employed to gain better prediction performance. Experimental results on four datasets demonstrate the superiority of TCL4KT over baseline models, and further analysis verifies the effectiveness of our three-view contrastive learning framework.