Intersection of education and deep learning method of artificial intelligence (AI) is gradually becoming a hot research field. Education will be profoundly transformed by AI. The purpose of this review is to help education practitioners understand the research frontiers and directions of AI applications in education. This paper reviews the…

The advent of artificial intelligence (AI), particularly large language models (LLMs) like ChatGPT and Gemini, has significantly impacted the educational landscape, offering unique opportunities for learning and assessment. In the realm of written assessment grading, traditionally viewed as a laborious and subjective process, this study sought to…

We systematically compared two coding approaches to generate training datasets for machine learning (ML): (1) a holistic approach based on learning progression levels; and (2) a dichotomous, analytic approach of multiple concepts in student reasoning, deconstructed from holistic rubrics. We evaluated four constructed response assessment items for…

Understanding student cognitive states is essential for assessing human learning. The deep neural networks (DNN)-inspired cognitive state prediction method improved prediction performance significantly; however, the lack of explainability with DNNs and the unitary scoring approach fail to reveal the factors influencing human learning. Identifying…

The biggest difference in statistical training from previous decades is the increased use of software. However, little research examines how software impacts learning statistics. Assessing the value of software to statistical learning demands appropriate, valid, and reliable measures. The present study expands the arsenal of tools by reporting on…

Multidimensional scoring evaluates each constructed-response answer from more than one rating dimension and/or trait such as lexicon, organization, and supporting ideas instead of only one holistic score, to help students distinguish between various dimensions of writing quality. In this work, we present a bilevel learning model for combining two…

Numeracy is important for everyday life. Being numerate has a positive impact on the quality of life of individuals, with positive economic, health, and social outcomes. Despite this, little is known about the role of numeracy in the lives of adults with intellectual disability (ID). Design research has been used to develop ways to support…

Automated scoring of student language is a complex task that requires systems to emulate complex and multi-faceted human evaluation criteria. Summary scoring brings an additional layer of complexity to automated scoring because it involves two texts of differing lengths that must be compared. In this study, we present our approach to automate…

In Automated Essay Scoring (AES) systems, many previous works have studied group fairness using the demographic features of essay writers. However, individual fairness also plays an important role in fair evaluation and has not been yet explored. Initialized by Dwork et al., the fundamental concept of individual fairness is "similar people…

We design a generative adversarial network (GAN)-based pencil drawing learning system for art education on large image datasets to help students study how to draw pencil drawings for images and scenes. The system generates a pencil drawing result for a natural image based on GAN. The GAN network is trained on pencil drawing big datasets containing…

Design Research (DR) has been used to develop means of supporting mathematical learning for typically-developing students. This study investigated the use of DR to develop context specific tools to support adults with intellectual disabilities (ID) to improve their numeracy capabilities and engagement in daily tasks. Using observation and…

Digitalization and automation of test administration, score reporting, and feedback provision have the potential to benefit large-scale and formative assessments. Many studies on automated essay scoring (AES) and feedback generation systems were published in the last decade, but few connected AES and feedback generation within a unified framework.…

We have the ability to capture data from students' interactions with digital environments as they engage in learning activity. This provides the potential for a reimagining of assessment to one in which assessment become part of our natural education activity and can be used to support learning. These new data allow us to more closely examine the…

Confidence assessment (CA) involves students stating alongside each of their answers a confidence rating (e.g. 0 low to 10 high) to express how certain they are that their answer is correct. Each student's score is calculated as the sum of the confidence ratings on the items that they answered correctly, minus the sum of the confidence ratings on…

Taking a test improves memory for that tested information, a finding referred to as the testing effect. Multiple-choice tests tend to produce smaller testing effects than do cued-recall tests, and this result is largely attributed to the different processing that the two formats are assumed to induce. Specifically, it is generally assumed that the…