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…

Large language models (LLMs), such as Codex, hold great promise in enhancing programming education by automatically generating feedback for students. We investigate using LLMs to generate feedback for fixing syntax errors in Python programs, a key scenario in introductory programming. More concretely, given a student's buggy program, our goal is…

Contribution: Most work on languages in computing education currently focuses on non-native speakers. In contrast, to the best of the authors' knowledge, this article is the first response to the call for research on terms that takes into account the terms used by novices in their language. Background: Terms are key factors in communication,…

Recent advancements in large language models (LLMs) hold significant promise for improving physics education research that uses machine learning. In this study, we compare the application of various models for conducting a large-scale analysis of written text grounded in a physics education research classification problem: identifying skills in…

Creating practice questions for programming learning is not an easy job. It requires the instructor to diligently organize heterogeneous learning resources. Although educational technologies have been adopted across levels of programming learning, programming question generation (PQG) is still predominantly performed by instructors without…

A multi-label variant of email classification named ML-EC[superscript 2] (multi-label email classification using clustering) has been proposed in this work. ML-EC[superscript 2] is a hybrid algorithm based on text clustering, text classification, frequent-term calculation (based on latent dirichlet allocation), and taxonomic term-mapping…

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 thriving developer community has a significant impact on the widespread use of R software. To better understand this community, we conducted a study analyzing all R packages available on CRAN. We identified the most popular topics of R packages by text mining the package descriptions. Additionally, using network centrality measures, we…

This study aimed to examine the potentials of the NLP approach in detecting discourse markers (DMs), namely okay, in transcribed spoken data. One hundred thirty-eight concordance lines were presented to human referees to judge the functions of okay in them as a DM or Non-DM. After that, the researchers used a Python script written according to the…

This dissertation is an inquiry into the history of Chinese computer-based word processing technologies from 1958 to 1997. My purpose in looking into the history is to answer, how the development and usage of word-processing technologies have contributed to knowledge production, by shaping the understanding of what information technologies can do.…

Background: Learning to code is increasingly embedded in secondary and higher education curricula, where solving programming exercises plays an important role in the learning process and in formative and summative assessment. Unfortunately, students admit that copying code from each other is a common practice and teachers indicate they rarely use…

This article is dedicated to the issue of morphological analysis and synthesis of word forms in a linguistic analyzer, which is a significant feature of corpus linguistics. The article discourses in detail the morphological analysis, the creation of artificial language, grammar and analyzer, the general scheme of the analysis program that…

Over the past decade, sociologists have become increasingly interested in the formal study of semantic relations within text. Most contemporary studies focus either on mapping concept co-occurrences or on measuring semantic associations via word embeddings. Although conducive to many research goals, these approaches share an important limitation:…

In addition to movies, television programs, and TED Talks presentations, podcasts are an increasingly popular form of media that promotes authentic public discourse for diverse audiences, including university professors and students. However, English language teachers in the English as a second language/English as a foreign language contexts might…

Until now, there has been very little unified analysis of metadiscourse across speech and writing. Drawing on a reflexive metadiscourse model, this article conducts a multidimensional analysis of metadiscourse across 10 spoken and written registers in a corpus of 626 texts. Two metadiscourse dimensions, participants' interaction and discourse…