Knowledge tracing, the act of modeling a student's knowledge through learning activities, is an extensively studied problem in the field of computer-aided education. Armed with attention mechanisms focusing on relevant information for target prediction, recurrent neural networks and Transformer-based knowledge tracing models have outperformed traditional approaches such as Bayesian knowledge tracing and collaborative filtering. However, the attention mechanisms of current state-of-the-art knowledge tracing models share two limitations. Firstly, the models fail to leverage deep self-attentive computations for knowledge tracing. As a result, they fail to capture complex relations among exercises and responses over time. Secondly, appropriate features for constructing queries, keys and values for the self-attention layer for knowledge tracing have not been extensively explored. The usual practice of using exercises and interactions (exercise-response pairs), as queries and keys/values, respectively, lacks empirical support.In this paper, we propose a novel Transformer-based model for knowledge tracing, SAINT: Separated Self-AttentIve Neural Knowledge Tracing. SAINT has an encoder-decoder structure where the exercise and response embedding sequences separately enter, respectively, the encoder and the decoder. The encoder applies self-attention layers to the sequence of exercise embeddings, and the decoder alternately applies selfattention layers and encoder-decoder attention layers to the sequence of response embeddings. This separation of input allows us to stack attention layers multiple times, resulting in an improvement in area under receiver operating characteristic curve (AUC). To the best of our knowledge, this is the first work to suggest an encoder-decoder model for knowledge tracing that applies deep self-attentive layers to exercises and responses separately.We empirically evaluate SAINT on a large-scale knowledge tracing dataset, EdNet, collected by an active mobile education

Advances in Artificial Intelligence in Education (AIEd) and the ever-growing scale of Interactive Educational Systems (IESs) have led to the rise of data-driven approaches for knowledge tracing and learning path recommendation. Unfortunately, collecting student interaction data is challenging and costly. As a result, there is no public largescale benchmark dataset reflecting the wide variety of student behaviors observed in modern IESs. Although several datasets, such as ASSISTments, Junyi Academy, Synthetic and STATICS are publicly available and widely used, they are not large enough to leverage the full potential of state-of-the-art data-driven models. Furthermore, the recorded behavior is limited to question-solving activities. To this end, we introduce EdNet, a large-scale hierarchical dataset of diverse student activities collected by Santa, a multi-platform self-study solution equipped with an artificial intelligence tutoring system. EdNet contains 131,417,236 interactions from 784,309 students collected over more than 2 years, making it the largest public IES dataset released to date. Unlike existing datasets, EdNet records a wide variety of student actions ranging from questionsolving to lecture consumption to item purchasing. Also, EdNet has a hierarchical structure which divides the student actions into 4 different levels of abstractions. The features of EdNet are domain-agnostic, allowing EdNet to be easily extended to different domains. The dataset is publicly released for research purposes. We plan to host challenges in multiple AIEd tasks with EdNet to provide a common ground for the fair comparison between different state-of-the-art models and to encourage the development of practical and effective methods.

We propose SAINT+, a successor of SAINT which is a Transformer based knowledge tracing model that separately processes exercise information and student response information. Following the architecture of SAINT, SAINT+ has an encoder-decoder structure where the encoder applies self-attention layers to a stream of exercise embeddings, and the decoder alternately applies self-attention layers and encoder-decoder attention layers to streams of response embeddings and encoder output. Moreover, SAINT+ incorporates two temporal feature embeddings into the response embeddings: elapsed time, the time taken for a student to answer, and lag time, the time interval between adjacent learning activities. We empirically evaluate the effectiveness of SAINT+ on EdNet, the largest publicly available benchmark dataset in the education domain. Experimental results show that SAINT+ achieves state-of-the-art performance in knowledge tracing with an improvement of 1.25% in area under receiver operating characteristic curve compared to SAINT, the current state-of-the-art model in EdNet dataset. CCS CONCEPTS• Computing methodologies → Artificial intelligence; Neural networks; • Applied computing → Interactive learning environments; • Social and professional topics → Student assessment.

With advances in Arti cial Intelligence in Education (AIEd) and the ever-growing scale of Interactive Educational Systems (IESs), data-driven approach has become a common recipe for various tasks such as knowledge tracing and learning path recommendation. Unfortunately, collecting real students' interaction data is o en challenging, which results in the lack of public large-scale benchmark dataset re ecting a wide variety of student behaviors in modern IESs. Although several datasets, such as ASSISTments, Junyi Academy, Synthetic and STATICS, are publicly available and widely used, they are not large enough to leverage the full potential of state-of-the-art data-driven models and limits the recorded behaviors to question-solving activities.To this end, we introduce EdNet, a large-scale hierarchical dataset of diverse student activities collected by Santa, a multi-platform self-study solution equipped with arti cial intelligence tutoring system. EdNet contains 131,417,236 interactions from 784,309 students collected over more than 2 years, which is the largest among the ITS datasets released to the public so far. Unlike existing datasets, EdNet provides a wide variety of student actions ranging from question-solving to lecture consumption and item purchasing. Also, EdNet has a hierarchical structure where the student actions are divided into 4 di erent levels of abstractions. e features of EdNet are domain-agnostic, allowing EdNet to be extended to di erent domains easily.e dataset is publicly released under Creative Commons A ribution-NonCommercial 4.0 International license for research purposes. We plan to host challenges in multiple AIEd tasks with EdNet to provide a common ground for the fair comparison between di erent state-of-the-art models and encourage the development of practical and e ective methods.

Student dropout prediction provides an opportunity to improve student engagement, which maximizes the overall effectiveness of learning experiences. However, researches on student dropout were mainly conducted on school dropout or course dropout, and study session dropout in a mobile learning environment has not been considered thoroughly. In this paper, we investigate the study session dropout prediction problem in a mobile learning environment. First, we define the concept of the study session, study session dropout and study session dropout prediction task in a mobile learning environment. Based on the definitions, we propose a novel Transformer based model for predicting study session dropout, DAS: Deep Attentive Study Session Dropout Prediction in Mobile Learning Environment. DAS has an encoder-decoder structure which is composed of stacked multi-head attention and point-wise feed-forward networks. The deep attentive computations in DAS are capable of capturing complex relations among dynamic student interactions. To the best of our knowledge, this is the first attempt to investigate study session dropout in a mobile learning environment. Empirical evaluations on a large-scale dataset show that DAS achieves the best performance with a significant improvement in area under the receiver operating characteristic curve compared to baseline models.