Humans have the remarkable ability to solve different tasks by simply reading textual instructions that define the tasks and looking at a few examples. Natural Language Processing (NLP) models built with the conventional machine learning paradigm, however, often struggle to generalize across tasks (e.g., a question-answering system cannot solve…

This study examines the effectiveness of artificial intelligence (AI) in psychological report writing by comparing reports generated by human psychologists with those produced by OpenAI's Generative Pre-trained Transformer Version 4 (ChatGPT-4). A total of 249 licensed psychologists evaluated the reports based on overall quality, readability,…

Current student-centred, multilingual, active teaching methodologies require that teachers have continuous access to texts that are adequate in terms of topic and language competence. However, the task of finding appropriate materials is arduous and time consuming for teachers. To build on automatic readability assessment research that could help…

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…

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…

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…

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,…

With the rapid advancement of generative artificial intelligence (GAI), its application in educational settings has increasingly become a focal point, particularly in enhancing students' analytical capabilities. This study examines the effectiveness of the ChatGPT prompt framework in improving text analysis skills among students, specifically…

This study examined the relationship of linguistic complexity, captured using a set of lexical richness, syntactic complexity, and discoursal complexity indices, to second language (L2) learners' perception of text difficulty, captured using L2 raters' comparative judgment on text comprehensibility and reading speed. Testing materials were 180…

Empirical evidence remains sparse about how videos enhanced with first-language (L1) and second-language (L2) subtitles influence cognitive load in L2 learners. To address this point, 25 Korean undergraduate students were exposed to six short videos: baseline, L1-subtitled, and L2-subtitled videos at both high and low difficulty levels (determined…

Background: Advances in natural language processing (NLP) and computational linguistics have facilitated major improvements on traditional readability formulas that aim at predicting the overall difficulty of a text. Recent studies have identified several types of linguistic features that are theoretically motivated and predictive of human…

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,…

For decades, educators have relied on readability metrics that tend to oversimplify dimensions of text difficulty. This study examines the potential of applying advanced artificial intelligence methods to the educational problem of assessing text difficulty. The combination of hierarchical machine learning and natural language processing (NLP) is…