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 explored the effectiveness of scaffolding in students' reflection writing process. We compared two sections of an introductory computer programming course (N=188). In Section 1, students did not receive any scaffolding while generating reflections, whereas in Section 2, students were scaffolded during the reflection writing process.…

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…

In an Intelligent Tutoring System (ITS), problem (or question) difficulty is one of the most critical parameters, directly impacting problem design, test paper organization, result analysis, and even the fairness guarantee. However, it is very difficult to evaluate the problem difficulty by organized pre-tests or by expertise, because these…

Conversational Intelligent Tutoring Systems (ITSs) are expensive to develop. While simple online courseware could be easily authored by teachers, the authoring of conversational ITSs usually involves a team of experts with different expertise, including domain experts, linguists, instruction designers, programmers, artists, computer scientists,…

As programming must be learned by doing, introductory programming course learners need to solve many problems, e.g., on systems such as 'Online Judges'. However, as such courses are often compulsory for non-Computer Science (nonCS) undergraduates, this may cause difficulties to learners that do not have the typical intrinsic motivation for…

As students learn how to program, both their programming code and their understanding of it evolves over time. In this work, we present a general data-driven approach, named "Temporal-ASTNN" for modeling student learning progression in open-ended programming domains. Temporal-ASTNN combines a novel neural network model based on abstract…

AutoTutor uses conversational intelligent agents in learning environments. One of the major challenges in developing AutoTutor applications is to assess students' natural language answers to AutoTutor questions. We investigated an AutoTutor dataset with 3358 student answers to 49 AutoTutor questions. In comparisons with human ratings, we found…

This paper reports on the ongoing international project "System architecture for ICALL" and the progress made by the Swedish partner. The Swedish team is developing a web-based exercise generator reusing available annotated corpora and lexical resources. Apart from the technical issues like implementation of the user interface and the…

Students in introductory programming classes often articulate their questions and information needs incompletely. Consequently, the automatic classification of student questions to provide automated tutorial responses is a challenging problem. This paper analyzes 411 questions from an introductory Java programming course by reducing the natural…

The ability to predict a student's performance could be useful in a great number of different ways associated with university-level learning. In this paper, a grammar guided genetic programming algorithm, G3P-MI, has been applied to predict if the student will fail or pass a certain course and identifies activities to promote learning in a…