Cloze items are a foundational approach to assessing readability. However, they require human data collection, thus making them impractical in automated metrics. The present study revisits the idea of assessing readability with cloze items and compares human cloze scores and readability judgments with predictions made by T5, a popular deep…

Worked examples, which present an explained code for solving typical programming problems are among the most popular types of learning content in programming classes. Most approaches and tools for presenting these examples to students are based on line-by-line explanations of the example code. However, instructors rarely have time to provide…

The ability to objectively quantify the complexity of a text can be a useful indicator of how likely learners of a given level will comprehend it. Before creating more complex models of assessing text difficulty, the basic building block of a text consists of words and, inherently, its overall difficulty is greatly influenced by the complexity of…

Response time has been used as an important predictor of student performance in various models. Much of this work is based on the hypothesis that if students respond to a problem step too quickly or too slowly, they are most likely to be unsuccessful in that step. However, something that is less explored is that students may cycle through…

Thirty-nine years ago, Bain and Poindexter (1981) implored higher educators of kinesiology to develop curricula that prepare students to use what they learn in practical ways. Lay resource material, however, often fails to meet metrics for adequate-to-optimal readability, regardless of who produces them. Research suggests that many people trained…

This paper systematically explores how Large Language Models (LLMs) generate explanations of code examples of the type used in intro-to-programming courses. As we show, the nature of code explanations generated by LLMs varies considerably based on the wording of the prompt, the target code examples being explained, the programming language, the…

While hierarchical machine learning approaches have been used to classify texts into different content areas, this approach has, to our knowledge, not been used in the automated assessment of text difficulty. This study compared the accuracy of four classification machine learning approaches (flat, one-vs-one, one-vs-all, and hierarchical) using…

Finding the optimal topic sequence of online courses requires experts with lots of knowledge about taught topics. Having a good order is necessary for a good learning experience. By using educational recommender systems across different platforms we have the problem that the connection to an ontology sometimes does not exist. Thus, the state of…

Text complexity has received increased attention due to the CCSS, which call for students to comprehend increasingly more complex texts as they progress through grades. Quantitative text complexity (or readability) indices are based on text attributes (e.g., sentence lengths, and lexical, syntactic, & semantic difficulty), quantified by…

Despite prevalent use and practical application, the current and standard assessment of oral reading fluency (ORF) presents considerable limitations which reduces its validity in estimating growth and monitoring student progress, including: (a) high cost of implementation; (b) tenuous passage equivalence; and (c) bias, large standard error, and…

Lack of reading fluency is a significant obstacle to children's ability to learn from text. In this study, we explored the effects of two practices used to scaffold fluency -- repeated reading of a passage and listening to a passage before reading it. Since the differences between these practices may be subtle, we employed eye tracking to measure…

Language is frequently discussed as barrier to mathematics word problems. Hence this paper presents the initial findings of a linguistic analysis of numeracy skills test sample items. The theoretical perspective of multi-modal text analysis underpinned this study, in which data was extracted from the ten sample numeracy test items released by the…

In this paper, we applied the crowdsourcing approach to develop an automated popularity summary scoring, called wild summaries. In contrast, the golden standard summaries generated by one or more experts are called expert summaries. The innovation of our study is to compute LSA (Latent Semantic Analysis) similarities between target summary and…

This paper reports the results from a sensor-free detector of mind wandering during an online reading task. Features consisted of reading behaviors (e.g., reading time) and textual features (e.g., level of difficulty) extracted from self-paced reading log files. Supervised machine learning was applied to two datasets in order to predict if…

Although a reader's text-level comprehension is affected by the comprehension of individual sentences in a text, little attention has been paid to the difficulty of sentences. This study investigates whether measures (features) of text difficulty affect the "gradience" observed in sentence difficulty judgments. We examine two traditional…