In educational systems, predictive models face significant challenges during initial deployment and when new students begin to use them or when new exercises are added to the system due to a lack of data for making initial inferences, often called the cold start problem. This paper tests logitdec and logitdecevol, "evolutionary" features…

The deepened understandings of the Double Reduction policy have instigated a transition from focusing on reduction in homework quantity to emphasizing homework quality in Chinese basic education. The digital transformation in education offers new opportunities to address the current issues with homework management, such as unscientific design of…

Program alignment with professional standards ensures that students gain competency-based skills that can be transferred to the workplace environment. Employers continue to place a greater value on these skills. Establishing curriculum alignment with professional standards can assist with annual program evaluations, student learning outcomes, and…

Technological advancements, particularly in the field of education, are influencing the future course of education and the process of acquiring knowledge. Prior studies have investigated the implementation of education technology (edtech), but has paid little attention on continuous intention of using it. This research broadens the application of…

In recent years, remarkable advancements in artificial intelligence technology have created new opportunities for transforming educational systems and enhancing student learning. This study focuses on designing a model for an AI-based intelligent assistant to provide a personalized learning experience in higher education. A qualitative approach…

The Unified Theory of Acceptance and Use of Technology (UTAUT) and its successor, UTAUT2, were widely recognised frameworks for understanding technology adoption in organisational and consumer contexts. UTAUT2 extended the original framework by introducing constructs such as hedonic motivation, price value, and habit, broadening its applicability…

MOOC platforms provide a means of communication through forums, allowing learners to express their difficulties and challenges while studying various courses. Within these forums, some posts require urgent attention from instructors. Failing to respond promptly to these posts can contribute to higher dropout rates and lower course completion…

Knowledge tracing (KT) models predict how students will perform on future interactions, given a sequence of prior responses. Modern approaches to KT leverage "deep learning" techniques to produce more accurate predictions, potentially making personalized learning paths more efficacious for learners. Many papers on the topic of KT focus…

This research aims to develop an adaptive digital project-based learning model enhanced with artificial intelligence technology to facilitate the creation of digital content. A systematic approach was employed, divided into three phases: 1) study and synthesis of conceptual frameworks to understand the elements and relationships of related…

Many technology acceptance models used in education were originally designed for general technologies and later adopted by education researchers. This study extends Davis' technology acceptance model to specifically evaluate educational technologies in higher education, focusing on virtual classrooms. Prior research informed the construction of…

Knowledge tracing (KT) models have been a commonly used tool for tracking students' knowledge status. Recent advances in deep knowledge tracing (DKT) have demonstrated increased performance for knowledge tracing tasks in many datasets. However, interpreting students' states on single knowledge components (KCs) from DKT models could be challenging…

Background: For decades, education researchers have relied on the work of Campbell, Cook, and Shadish to help guide their thinking about valid impact estimates in the social sciences (Campbell & Stanley, 1963; Shadish et al., 2002). The foundation of this work is the "validity typology" and its associated "threats to…

The integration of Internet technology and the collaborative development of smart classrooms is an essential step for colleges and universities to advance English instruction reform. This study utilized data mining (DM) technology to analyze the learning process in college English smart classrooms. The results indicate that the DM algorithm used…

Educational technology terminology is messy. The same meaning is often expressed using several terms. More confusingly, some terms are used with several meanings. This state is unfortunate, as it makes both research and development more difficult. Terminology is particularly important in the case of personalization techniques, where the nuances of…

Deep learning models for text classification have been increasingly used in intelligent tutoring systems and educational writing assistants. However, the scarcity of data in many educational settings, as well as certain imbalances in counts among the annotated labels of educational datasets, limits the generalizability and expressiveness of…