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…

This study explores the potential of large language models (LLMs), specifically GPT-4 and Gemini, in generating teaching cases for information systems courses. A unique prompt for writing three different types of teaching cases such as a descriptive case, a normative case, and a project-based case on the same IS topic (i.e., the introduction of…

Although text readability has traditionally been measured based on simple linguistic features, recent studies have employed natural language processing techniques to develop new readability formulas that better represent theoretical accounts of reading processes. This study evaluated the construct validity of different readability formulas,…

This report sets out the findings of the technical development work completed as part of the Use Cases for Generative AI in Education project, commissioned by the Department for Education (DfE) in September 2023. It has been published alongside the User Research Report, which sets out the findings from the ongoing user engagement activity…

Unfolding models are frequently used to develop scales for measuring attitudes. Recently, unfolding models have been applied to examine rater severity and accuracy within the context of rater-mediated assessments. One of the problems in applying unfolding models to rater-mediated assessments is that the substantive interpretations of the latent…

We conducted two experiments to assess the alignment between Generative AI (GenAI) text personalization and hypothetical readers' profiles. In Experiment 1, four LLMs (i.e., Claude 3.5 Sonnet; Llama; Gemini Pro 1.5; ChatGPT 4) were prompted to tailor 10 science texts (i.e., biology, chemistry, physics) to accommodate four different profiles…

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…

This study examined 283 online learner dictionary definitions in terms of scores based on word frequency level and readability. Results revealed three findings. First, in terms of word frequency levels, definitions from the Cambridge learner dictionary incorporated fewer non-high frequency words (mid and low frequency words) compared to Oxford,…

Online patient portals that facilitate communication between patient and provider can improve patients' medication adherence and health outcomes. The effectiveness of such web-based communication measures can be influenced by the health literacy (HL) of a patient. In the context of diabetes, low HL is associated with severe hypoglycemia and high…

Purpose: The purpose of this study is to examine student sentiments regarding high-quality vs low-quality teaching. Design/methodology/approach: This study uses a text mining technique to identify the positive and negative patterns of student sentiments from student evaluations of teaching (SET) provided on Ratemyprofessors.com. After identifying…

Graded reading is one of the important ways of English learning. How to automatically judge and grade the difficulty of the English reading corpus is of great significance for precision teaching and personalized learning. However, the current rule-based readability assessment methods have some limitations, such as low efficiency and poor accuracy.…

This paper examines links between perfect rhymes and text readability and decoding using a measure of English rhymes called the Perfect Rhymes Dictionary (PeRDict). PeRDict is based on the Carnegie Mellon University Pronouncing Dictionary (the CMUdict) and provides rhyme counts for ~48,000 words in English and for the most frequent 1,000, 2,500,…

Metadiscourse is a tool for writers to guide and interact with readers through texts. Yet in most student texts, one of the points lacking is the interaction between writers and readers. In this study, frequency and type of interactive and interactional metadiscourse features were explored via students' research-based essays based on Hyland's…

However influential the interdependence hypothesis has become in bilingual research, it still lacks full empirical support. This longitudinal study explores the parallels in the biliteracy development (L1 Spanish and L2 English) of 20 students in a European immersion programme (i.e. CLIL) over a two-year period. A bilingual learner corpus of…

Reading texts may serve as a vital source of informational content and language knowledge for second language (L2) learners, which is known as the dual relevance of L2 reading (Han & D'Angelo, 2009). Text complexity, however, influences the two, determining to a great extent whether the dual outcome is attainable. Drawing on Complex Dynamic…