This study investigates the differential impacts of various online language assessment models--specifically, the Nonlinear Dynamic Individual-Centered Language Assessment (NDICLA), diagnostic assessment, and formative assessment--on the cognitive load and learning outcomes of English as a Foreign Language (EFL) learners within computer-assisted…

This study mined student interactions with visual representations as a means to automate assessment of learning in a complex, inquiry-based learning environment. Log trace data of 143 middle school students' interactions with an interactive map in Research Quest (an inquiry-based, online learning environment) were analyzed. Students used the…

The flipped classroom gives students the flexibility to organize their learning, while teachers can monitor their progress analyzing their online activity. In massive courses where there are a variety of activities, automated analysis techniques are required in order to process the large volume of information that is generated, to help teachers…

As digital technology is becoming an increasingly critical component of education, learners' socioeconomic status (SES) and technology use are becoming more important in their learning. In the context of English learning, the present study modeled how learners' SES and their perception of technology use for language learning are linked to their…

Computer-mediated learning initiatives have recently increased due to the novel coronavirus pandemic. Implications are thus created for self-regulation, learning and achievement as computer-mediated learners face unique motivational and metacognitive demands. The current research uses a serial mediation approach to test the effect of goal…

How can we learn to use properly business software, digital environments, games or intelligent tutoring systems (ITS)? Mainly, we assume that the new user will learn by doing. But what about the efficiency of such a method? Our approach proposes an answer by introducing on-line coaching. In learning process, learners may need guidance to help them…

The use of machine learning with educational data mining (EDM) to predict learner performance has always been an important research area. Predicting academic results is one of the solutions that aims to monitor the progress of students and anticipates students at risk of failing the academic pathways. In this paper, we present a framework for…

After the outbreak of the COVID-19 pandemic, China implemented the largest online education practice in human history. In the process, different teaching models coexist. Through a quasi-natural experiment, a total of 1,024 samples from Guiyang No.8 Middle School and another comparable school with the same conditions and students were enrolled for…

After the outbreak of the COVID-19 pandemic, China implemented the largest online education practice in human history. In the process, different teaching models coexist. Through a quasi-natural experiment, a total of 1,024 samples from Guiyang No.8 Middle School and another comparable school with the same conditions and students were enrolled for…

The purpose of this paper is to reexamine the effect of internal school factors such as school violence and class size, and external school factors such as family socio-economic resources on student math achievements, based on the social ecological model, eliciting an integrative approach. Data were collected from an Israeli national database,…

Students of Southeast Asian Heritage Learning Chinese (SSAHLC) in Taiwan have frequently demonstrated difficulty with traditional Chinese (a graphical character) radical recognition due to their limited exposure to the written language form since childhood. In this study, we designed a Chinese radical learning game (CRLG), which adopted a drill…

Previous research has indicated the disconnect between example-based research focusing on worked examples (WEs) and that focusing on modeling examples. The purpose of this study was to examine and compare the effect of four different types of examples from the two separate lines of research, including standard WEs, erroneous WEs, expert (masterly)…

Considering the increasing importance of adaptive approaches in CALL systems, this study implemented a machine learning based student modeling middleware with Bayesian networks. The profiling approach of the student modeling system is based on Felder and Silverman's Learning Styles Model and Felder and Soloman's Index of Learning Styles…

Many students lack adequate mathematic skills and must enroll in developmental math programs to satisfy the math requirement to earn a college degree, but developmental programs are often problematic with high failure rates, preventing graduation. This study examined whether the emporium model, a computer-based developmental math tool, was more…

A personalized e-learning service provides learning content to fit learners' individual differences. Learning achievements are influenced by cognitive as well as non-cognitive factors such as mood, motivation, interest, and personal styles. This paper proposes the Learning Caution Indexes (LCI) to detect aberrant learning patterns. The philosophy…