arXiv subjects

Hieke Keuning

Publications and source records attributed to Hieke Keuning.

18 recordsLinked to original sources

arXiv2025

Understanding Student Interaction with AI-Powered Next-Step Hints: Strategies and Challenges

Automated feedback generation plays a crucial role in enhancing personalized learning experiences in computer science education. Among different types of feedback, next-step hint feedback is particularly important, as it provides students with actionable steps to progress towards solving programming tasks. This study investigates how students interact with an AI-driven next-step hint system in an in-IDE learning environment. We gathered and analyzed a dataset from 34 students solving Kotlin tasks, containing detailed hint interaction logs. We applied process mining techniques and identified 16 common interaction scenarios. Semi-structured interviews with 6 students revealed strategies for managing unhelpful hints, such as adapting partial hints or modifying code to generate variations of the same hint. These findings, combined with our publicly available dataset, offer valuable opportunities for future research and provide key insights into student behavior, helping improve hint design for enhanced learning support.

cs.SE↗

arXiv2025

Excited, Skeptical, or Worried? A Multi-Institutional Study of Student Views on Generative AI in Computing Education

The application of Artificial Intelligence, in particular Generative AI, has become more widespread among educational institutions. Opinions vary widely on whether integrating AI into classrooms is the way forward or if it is detrimental to the quality of education. Increasingly, research studies are giving us more insight into the consequences of using AI tools in learning and teaching. Studies have shown how, when, and why students use AI tools. Because developments regarding the technology and its use are moving fast, we need frequent, ongoing, and more fine-grained investigation. One aspect that we do not know much about yet is how students use and think about AI across \textit{different types of education}. In this paper, we present the results of a multi-institutional survey with responses from 410 students enrolled in the computing programs of 23 educational institutions, representing high schools, colleges, and research universities. We found distinct usage patterns across the three educational institution types. Students from all types express excitement, optimism, and gratitude toward GenAI. Students in higher education more often report worry and skepticism, while high school students report greater trust and fewer negative feelings. Additionally, the AI hype has had a minimal influence, positive or negative, on high school students' decision to pursue computing. Our study contributes to a better understanding of inter-institutional differences in AI usage and perception and can help educators and students better prepare for future challenges related to AI in computing education.

cs.CY↗

arXiv2025

KOALA: a Configurable Tool for Collecting IDE Data When Solving Programming Tasks

Collecting data of students solving programming tasks is incredibly valuable for researchers and educators. It allows verifying that the students correctly apply the features and concepts they are taught, or finding students' misconceptions. However, existing data collection tools have limitations, e.g., no control over the granularity of the collected code, not collecting the specific events of the programming environment used, and overall being hard to configure. To overcome these limitations, we propose KOALA, a convenient and highly configurable tool for collecting code snapshots and feature usage from students solving programming tasks in JetBrains IDEs. The plugin can be installed in IDEs and configured to provide the students with the necessary tasks, enable or disable certain IDE features like code completion, and run surveys. During problem solving, the plugin collects code snapshots at the configured granularity, all IDE actions like running and debugging, as well as some data not collected in prior works, like employed hotkeys and switching focus between files. The collected data is sent to the server that comes with the tool, where it is stored and can be converted to the standardized ProgSnap2 format. To showcase the tool, we collected data from 28 students solving tasks in two courses within the IDE, highlighting some insights from this data.

cs.SE↗

arXiv2025

Student's Use of Generative AI as a Support Tool in an Advanced Web Development Course

Various studies have studied the impact of Generative AI on Computing Education. However, they have focused on the implications for novice programmers. In this experience report, we analyze the use of GenAI as a support tool for learning, creativity, and productivity in a web development course for undergraduate students with extensive programming experience. We collected diverse data (assignments, reflections, logs, and a survey) and found that students used GenAI on different tasks (code generation, idea generation, etc.) with a reported increase in learning and productivity. However, they are concerned about over-reliance and incorrect solutions and want more training in prompting strategies.

cs.CY↗

arXiv2025

Teaching Well-Structured Code: A Literature Review of Instructional Approaches

Teaching the software engineers of the future to write high-quality code with good style and structure is important. This systematic literature review identifies existing instructional approaches, their objectives, and the strategies used for measuring their effectiveness. Building on an existing mapping study of code quality in education, we identified 53 papers on code structure instruction. We classified these studies into three categories: (1) studies focused on developing or evaluating automated tools and their usage (e.g., code analyzers, tutors, and refactoring tools), (2) studies discussing other instructional materials, such as learning resources (e.g., refactoring lessons and activities), rubrics, and catalogs of violations, and (3) studies discussing how to integrate code structure into the curriculum through a holistic approach to course design to support code quality. While most approaches use analyzers that point students to problems in their code, incorporating these tools into classrooms is not straightforward. Combined with further research on code structure instruction in the classroom, we call for more studies on effectiveness. Over 40% of instructional studies had no evaluation. Many studies show promise for their interventions by demonstrating improvement in student performance (e.g., reduced violations in student code when using the intervention compared with code that was written without access to the intervention). These interventions warrant further investigation on learning, to see how students apply their knowledge after the instructional supports are removed.

cs.SE↗

arXiv2025

In-IDE Programming Courses: Learning Software Development in a Real-World Setting

While learning programming languages is crucial for software engineers, mastering the necessary tools is equally important. To facilitate this, JetBrains recently released the JetBrains Academy plugin, which customizes the IDE for learners, allowing tutors to create courses entirely within IDE. In this work, we provide the first exploratory study of this learning format. We carried out eight one-hour interviews with students and developers who completed at least one course using the plugin, inquiring about their experience with the format, the used IDE features, and the current shortcomings. Our results indicate that learning inside the IDE is overall welcomed by the learners, allowing them to study in a more realistic setting, using features such as debugging and code analysis, which are crucial for real software development. With the collected results and the analysis of the current drawbacks, we aim to contribute to teaching students more practical skills.

cs.SE↗

arXiv2024

You're (Not) My Type -- Can LLMs Generate Feedback of Specific Types for Introductory Programming Tasks?

Background: Feedback as one of the most influential factors for learning has been subject to a great body of research. It plays a key role in the development of educational technology systems and is traditionally rooted in deterministic feedback defined by experts and their experience. However, with the rise of generative AI and especially Large Language Models (LLMs), we expect feedback as part of learning systems to transform, especially for the context of programming. In the past, it was challenging to automate feedback for learners of programming. LLMs may create new possibilities to provide richer, and more individual feedback than ever before. Objectives: This paper aims to generate specific types of feedback for introductory programming tasks using LLMs. We revisit existing feedback taxonomies to capture the specifics of the generated feedback, such as randomness, uncertainty, and degrees of variation. Methods: We iteratively designed prompts for the generation of specific feedback types (as part of existing feedback taxonomies) in response to authentic student programs. We then evaluated the generated output and determined to what extent it reflected certain feedback types. Results and Conclusion: The present work provides a better understanding of different feedback dimensions and characteristics. The results have implications for future feedback research with regard to, for example, feedback effects and learners' informational needs. It further provides a basis for the development of new tools and learning systems for novice programmers including feedback generated by AI.

cs.AI↗

arXiv2024

Investigating Student Reasoning in Method-Level Code Refactoring: A Think-Aloud Study

Producing code of good quality is an essential skill in software development. Code quality is an aspect of software quality that concerns the directly observable properties of code, such as decomposition, modularization, and code flow. Code quality can often be improved by means of code refactoring -- an internal change made to code that does not alter its observable behavior. According to the ACM/IEEE-CS/AAAI Computer Science Curricula 2023, code refactoring and code quality are core topics in software engineering education. However, studies show that students often produce code with persistent quality issues. Therefore, it is important to understand what problems students experience when trying to identify and fix code quality issues. In a prior study, we identified a number of student misconceptions in method-level code refactoring. In this paper, we present the findings from a think-aloud study conducted to investigate what students think when working on method-level refactoring exercises. We use grounded theory to identify and classify student reasoning. As a result of the analysis, we identify a set of eight reasons given by students to refactor code, which either concerns the presence of code quality issues, the improvement of software quality attributes, or code semantics. We also analyze which quality issues are identified by students, and to which reasonings these quality issues are related. We found that experienced students reason more often about code quality attributes rather than pointing at a problem they see in the code. Students were able to remove code quality issues in most cases. However, they often overlooked particular issues, such as the presence of a method with multiple responsibilities or the use of a less suitable loop structure.

cs.SE↗

arXiv2024

One Step at a Time: Combining LLMs and Static Analysis to Generate Next-Step Hints for Programming Tasks

Students often struggle with solving programming problems when learning to code, especially when they have to do it online, with one of the most common disadvantages of working online being the lack of personalized help. This help can be provided as next-step hint generation, i.e., showing a student what specific small step they need to do next to get to the correct solution. There are many ways to generate such hints, with large language models (LLMs) being among the most actively studied right now. While LLMs constitute a promising technology for providing personalized help, combining them with other techniques, such as static analysis, can significantly improve the output quality. In this work, we utilize this idea and propose a novel system to provide both textual and code hints for programming tasks. The pipeline of the proposed approach uses a chain-of-thought prompting technique and consists of three distinct steps: (1) generating subgoals - a list of actions to proceed with the task from the current student's solution, (2) generating the code to achieve the next subgoal, and (3) generating the text to describe this needed action. During the second step, we apply static analysis to the generated code to control its size and quality. The tool is implemented as a modification to the open-source JetBrains Academy plugin, supporting students in their in-IDE courses. To evaluate our approach, we propose a list of criteria for all steps in our pipeline and conduct two rounds of expert validation. Finally, we evaluate the next-step hints in a classroom with 14 students from two universities. Our results show that both forms of the hints - textual and code - were helpful for the students, and the proposed system helped them to proceed with the coding tasks.

cs.SE↗

arXiv2024

Students' Perceptions and Use of Generative AI Tools for Programming Across Different Computing Courses

Investigation of students' perceptions and opinions on the use of generative artificial intelligence (GenAI) in education is a topic gaining much interest. Studies addressing this are typically conducted with large heterogeneous groups, at one moment in time. However, how students perceive and use GenAI tools can potentially depend on many factors, including their background knowledge, familiarity with the tools, and the learning goals and policies of the courses they are taking. In this study we explore how students following computing courses use GenAI for programming-related tasks across different programs and courses: Bachelor and Master, in courses in which learning programming is the learning goal, courses that require programming as a means to achieve another goal, and in courses in which programming is optional, but can be useful. We are also interested in changes over time, since GenAI capabilities are changing at a fast pace, and users are adopting GenAI increasingly. We conducted three consecutive surveys (fall `23, winter `23, and spring `24) among students of all computing programs of a large European research university. We asked questions on the use in education, ethics, and job prospects, and we included specific questions on the (dis)allowed use of GenAI tools in the courses they were taking at the time. We received 264 responses, which we quantitatively and qualitatively analyzed, to find out how students have employed GenAI tools across 59 different computing courses, and whether the opinion of an average student about these tools evolves over time. Our study contributes to the emerging discussion of how to differentiate GenAI use across different courses, and how to align its use with the learning goals of a computing course.

cs.CY↗

arXiv2024

Clustering MOOC Programming Solutions to Diversify Their Presentation to Students

In many MOOCs, whenever a student completes a programming task, they can see previous solutions of other students to find potentially different ways of solving the problem and to learn new coding constructs. However, a lot of MOOCs simply show the most recent solutions, disregarding their diversity or quality, and thus hindering the students' opportunity to learn. In this work, we explore this novel problem for the first time. To solve it, we adapted the existing plagiarism detection tool JPlag to Python submissions on Hyperskill, a popular MOOC platform. However, due to the tool's inner algorithm, JPLag fully processed only 46 out of 867 studied tasks. Therefore, we developed our own tool called Rhubarb. This tool first standardizes solutions that are algorithmically the same, then calculates the structure-aware edit distance between them, and then applies clustering. Finally, it selects one example from each of the largest clusters, thus ensuring their diversity. Rhubarb was able to handle all 867 tasks successfully. We compared different approaches on a set of 59 real-life tasks that both tools could process. Eight experts rated the selected solutions based on diversity, code quality, and usefulness. The default platform approach of simply selecting recent submissions received on average 3.12 out of 5, JPlag - 3.77, Rhubarb - 3.50. To ensure both quality and coverage, we created a system that combines both tools. We conclude our work by discussing the future of this new problem and the research needed to solve it better.

cs.SE↗

arXiv2023

Next-Step Hint Generation for Introductory Programming Using Large Language Models

Large Language Models possess skills such as answering questions, writing essays or solving programming exercises. Since these models are easily accessible, researchers have investigated their capabilities and risks for programming education. This work explores how LLMs can contribute to programming education by supporting students with automated next-step hints. We investigate prompt practices that lead to effective next-step hints and use these insights to build our StAP-tutor. We evaluate this tutor by conducting an experiment with students, and performing expert assessments. Our findings show that most LLM-generated feedback messages describe one specific next step and are personalised to the student's code and approach. However, the hints may contain misleading information and lack sufficient detail when students approach the end of the assignment. This work demonstrates the potential for LLM-generated feedback, but further research is required to explore its practical implementation.

cs.CY↗

arXiv2023

What Skills Do You Need When Developing Software Using ChatGPT? (Discussion Paper)

Since the release of LLM-based tools such as GitHub Copilot and ChatGPT the media and popular scientific literature, but also journals such as the Communications of the ACM, have been flooded with opinions how these tools will change programming. The opinions range from ``machines will program themselves'', to ``AI does not help programmers''. Of course, these statements are meant to to stir up a discussion, and should be taken with a grain of salt, but we argue that such unfounded statements are potentially harmful. Instead, we propose to investigate which skills are required to develop software using LLM-based tools. In this paper we report on an experiment in which we explore if Computational Thinking (CT) skills predict the ability to develop software using LLM-based tools. Our results show that the ability to develop software using LLM-based tools can indeed be predicted by the score on a CT assessment. There are many limitations to our experiment, and this paper is also a call to discuss how to approach, preferably experimentally, the question of which skills are required to develop software using LLM-based tools. We propose to rephrase this question to include by what kind of people/programmers, to develop what kind of software using what kind of LLM-based tools.

cs.SE↗

arXiv2023

The Robots are Here: Navigating the Generative AI Revolution in Computing Education

Recent advancements in artificial intelligence (AI) are fundamentally reshaping computing, with large language models (LLMs) now effectively being able to generate and interpret source code and natural language instructions. These emergent capabilities have sparked urgent questions in the computing education community around how educators should adapt their pedagogy to address the challenges and to leverage the opportunities presented by this new technology. In this working group report, we undertake a comprehensive exploration of LLMs in the context of computing education and make five significant contributions. First, we provide a detailed review of the literature on LLMs in computing education and synthesise findings from 71 primary articles. Second, we report the findings of a survey of computing students and instructors from across 20 countries, capturing prevailing attitudes towards LLMs and their use in computing education contexts. Third, to understand how pedagogy is already changing, we offer insights collected from in-depth interviews with 22 computing educators from five continents who have already adapted their curricula and assessments. Fourth, we use the ACM Code of Ethics to frame a discussion of ethical issues raised by the use of large language models in computing education, and we provide concrete advice for policy makers, educators, and students. Finally, we benchmark the performance of LLMs on various computing education datasets, and highlight the extent to which the capabilities of current models are rapidly improving. Our aim is that this report will serve as a focal point for both researchers and practitioners who are exploring, adapting, using, and evaluating LLMs and LLM-based tools in computing classrooms.

cs.CY↗

arXiv2023

Exploring the Potential of Large Language Models to Generate Formative Programming Feedback

Ever since the emergence of large language models (LLMs) and related applications, such as ChatGPT, its performance and error analysis for programming tasks have been subject to research. In this work-in-progress paper, we explore the potential of such LLMs for computing educators and learners, as we analyze the feedback it generates to a given input containing program code. In particular, we aim at (1) exploring how an LLM like ChatGPT responds to students seeking help with their introductory programming tasks, and (2) identifying feedback types in its responses. To achieve these goals, we used students' programming sequences from a dataset gathered within a CS1 course as input for ChatGPT along with questions required to elicit feedback and correct solutions. The results show that ChatGPT performs reasonably well for some of the introductory programming tasks and student errors, which means that students can potentially benefit. However, educators should provide guidance on how to use the provided feedback, as it can contain misleading information for novices.

cs.AI↗

arXiv2023

A Systematic Mapping Study of Code Quality in Education -- with Complete Bibliography

While functionality and correctness of code has traditionally been the main focus of computing educators, quality aspects of code are getting increasingly more attention. High-quality code contributes to the maintainability of software systems, and should therefore be a central aspect of computing education. We have conducted a systematic mapping study to give a broad overview of the research conducted in the field of code quality in an educational context. The study investigates paper characteristics, topics, research methods, and the targeted programming languages. We found 195 publications (1976-2022) on the topic in multiple databases, which we systematically coded to answer the research questions. This paper reports on the results and identifies developments, trends, and new opportunities for research in the field of code quality in computing education.

cs.SE↗

arXiv2023

Detecting Code Quality Issues in Pre-written Templates of Programming Tasks in Online Courses

In this work, we developed an algorithm for detecting code quality issues in the templates of online programming tasks, validated it, and conducted an empirical study on the dataset of student solutions. The algorithm consists of analyzing recurring unfixed issues in solutions of different students, matching them with the code of the template, and then filtering the results. Our manual validation on a subset of tasks demonstrated a precision of 80.8% and a recall of 73.3%. We used the algorithm on 415 Java tasks from the JetBrains Academy platform and discovered that as much as 14.7% of tasks have at least one issue in their template, thus making it harder for students to learn good code quality practices. We describe our results in detail, provide several motivating examples and specific cases, and share the feedback of the developers of the platform, who fixed 51 issues based on the output of our approach.

cs.SE↗

arXiv2023

Analyzing the Quality of Submissions in Online Programming Courses

Programming education should aim to provide students with a broad range of skills that they will later use while developing software. An important aspect in this is their ability to write code that is not only correct but also of high quality. Unfortunately, this is difficult to control in the setting of a massive open online course. In this paper, we carry out an analysis of the code quality of submissions from JetBrains Academy - a platform for studying programming in an industry-like project-based setting with an embedded code quality assessment tool called Hyperstyle. We analyzed more than a million Java submissions and more than 1.3 million Python submissions, studied the most prevalent types of code quality issues and the dynamics of how students fix them. We provide several case studies of different issues, as well as an analysis of why certain issues remain unfixed even after several attempts. Also, we studied abnormally long sequences of submissions, in which students attempted to fix code quality issues after passing the task. Our results point the way towards the improvement of online courses, such as making sure that the task itself does not incentivize students to write code poorly.

cs.SE↗