The adaptive learning problem concerns how to create an individualized learning plan (also referred to as a learning policy) that chooses the most appropriate learning materials based on a learner's latent traits. In this article, we study an important yet less-addressed adaptive learning problem--one that assumes continuous latent traits.…

Personalized education systems recommend learning contents to students based on their capacity to accelerate their learning. This paper proposes a personalized exercise recommendation system for online self-directed learning. We first improve the performance of knowledge tracing models. Existing deep knowledge tracing models, such as Dynamic…

As one of the fundamental tasks in the online learning platform, interactive course recommendation (ICR) aims to maximize the long-term learning efficiency of each student, through actively exploring and exploiting the student's feedbacks, and accordingly conducting personalized course recommendation. Recently, deep reinforcement learning (DRL)…

Deep Reinforcement Learning (DRL) has been shown to be a very powerful technique in recent years on a wide range of applications. Much of the prior DRL work took the "online" learning approach. However, given the challenges of building accurate simulations for modeling student learning, we investigated applying DRL to induce a…

Deep reinforcement learning using convolutional neural networks is the technology behind autonomous vehicles. Could this same technology facilitate the road to college? During the summer between high school and college, college-related tasks that students must navigate can hinder successful matriculation. We employ conversational artificial…

Language learners need to map a continuous, multidimensional acoustic signal to discrete abstract speech categories. The complexity of this mapping poses a difficult learning problem, particularly for second language learners who struggle to acquire the speech sounds of a non-native language, and almost never reach native-like ability. A common…

Since the 1960s, researchers have been trying to optimize the sequencing of instructional activities using the tools of reinforcement learning (RL) and sequential decision making under uncertainty. Many researchers have realized that reinforcement learning provides a natural framework for optimal instructional sequencing given a particular model…

While Reinforcement learning (RL), especially Deep RL (DRL), has shown outstanding performance in video games, little evidence has shown that DRL can be successfully applied to human-centric tasks where the ultimate RL goal is to make the "human-agent interactions" productive and fruitful. In real-life, complex, human-centric tasks, such…

COVID-19 presented a challenge to the traditional methods of teaching programming and robotics in a secondary school environment. When campuses were closed around the world in the spring of 2020, it was not possible for students to access the computer labs nor the robotics equipment that was traditionally used to facilitate the instruction of…

In interactive e-learning environments such as Intelligent Tutoring Systems, pedagogical decisions can be made at different levels of granularity. In this work, we focus on making decisions at "two levels": whole problems vs. single steps and explore three types of granularity: "problem-level only" ("Prob-Only"),…

Active Learning Strategy is a significant and effective learning approach to ensure student engagement in learning sessions and enhancing understanding of the contents. Active learning with high motivation and deep learning will encourage students to plan, monitor and to evaluate the learning process and manage thought activities. This…

The purpose of this study was to examine the relationship between teaching quality and students' harmonious passion, deep strategy to learn, and epistemic curiosity in mathematics in 1,003 high school students. Data were analyzed using multilevel structural equation modeling, and results showed support for the hypotheses tested. First, we found…

Second language (L2) learners' awareness of first language-second language (L1-L2) semantic differences plays a critical role in L2 vocabulary learning. This study investigates the long-term development of eight university-level Chinese English as a foreign language learners' cross-linguistic semantic awareness over the course of 10 months. A…

One in six Americans is currently affected by neurologic disease. As the United States population ages, the number of neurologic complaints is expected to increase. Thus, there is a pressing need for more neurologists as well as more neurology training in other specialties. Often interest in neurology begins during medical school, so improving…

The Better Math Teaching Network (BMTN) is a networked improvement community of researchers, teachers, and instructional leaders from New England who use improvement science principles to increase the number of students who are actively and deeply engaged in algebra content. The BMTN's second year of implementation occurred during the 2017-18…