Supervised machine learning has become one of the most important methods for developing educational and intelligent tutoring software; it is the backbone of many educational data mining methods for estimating knowledge, emotion, and other aspects of learning. Hence, in order to ensure optimal utilization of computing resources and effective…

Cloze items are commonly used for both assessing learning and as a learning activity. This paper investigates the selection of sentences for cloze item creation by comparing methods ranging from simple heuristics to deep learning summarization models. An evaluation using human-generated cloze items from three different science texts indicates that…

Teachers increasingly rely on online social media platforms to supplement their educational resources, greatly influencing PK-12 education through the swift and extensive diffusion of teacher-curated resources. Understanding this diffusion process is crucial, but current educational studies primarily report resource diffusion through small-scale…

The COVID-19 pandemic has had a massive impact on education systems in the U.S, prompting a variety of changes to school learning environments. This study investigates student/family choices of learning modality in one large school district in the U.S and examines how these choices differ by students' race/ethnicity and performance level. Results…

We explored a series of feature selection methods for model-based Reinforcement Learning (RL). More specifically, we explored four common correlation metrics and based on them, we proposed the fifth one named Weighed Information Gain (WIG). While much existing correlation-based feature selection methods mostly explored high correlation by default,…

Studies examining feedback in educational settings have largely focused on feedback that is received, rather than chosen, by students. This study investigates whether adult participants learn more from choosing rather than receiving feedback from virtual characters in a digital poster design task. We employed a yoked study design and two versions…

Assuming the role of learning curators, 22 graduate students (in-service teachers) addressed authentic problems (challenges) within their respective classrooms by selecting digital tools as part of implementation of interdisciplinary lesson plans. Students focused on formative assessment tools as a means to gather evidence to make improvements in…

This study compares the four existing procedures handling the item selection in severely constrained computerized adaptive tests (CAT). These procedures include weighted deviation model (WDM), weighted penalty model (WPM), maximum priority index (MPI), and shadow test approach (STA). Severely constrained CAT refer to those adaptive tests seeking…

Since the mid-1970s, music education researchers studied and followed musicians' and non-musicians' views of music instrument gender stereotypes and associations. To understand instrument gender stereotypes, one must first understand the difference between sex and gender and gender's role in society. This research aims to study the views of…

Making one's own learning choices is central to self-directed learning, yet the opportunity to choose learning activities is rarely given to students in formal educational settings. The case study reported in this paper is a description of student experiences and perceptions in a software tools graduate level class that offered substantial…

In Learning Networks, learners need to share knowledge with others to build knowledge. In particular, when working on complex tasks, they often need to acquire extra cognitive resources from others to process a high task load. However, without support high task load and organizing knowledge sharing themselves might easily overload learners'…

This project explored ways in which student selection in nursing can be developed. Original research was undertaken throughout the United Kingdom using qualitative interviews with a range of academic staff and partners from practice. A conceptual framework was produced which identified five categories which can confidently be seen as…

The purpose of this paper is to describe the development of a framework to facilitate the selection and evaluation of picture books that may be useful in promoting and developing mathematical concepts in young children. Three types of mathematical picture books were initially recognised with intercoder reliability of 0.92. Seven categories were…

A program of Assessment for Learning (AfL) was implemented with 107 Year 12 students as part of their preparation for a major external test. Students completed extended mathematics tasks and selected student responses were used for peer assessment purposes. This paper reports on two of the AfL elements, namely task selection and peer assessment as…

As part of a larger project, "Task Types in Mathematics Learning," through the use of a questionnaire, we sought middle years mathematics teachers' insights into the task types they chose to use in mathematics, the reasons for these choices, and the ways (if any) in which their choices had changed as a result of their involvement in the…