Toward Finding and Supporting Struggling Students in a Programming Course with an Early Warning System

• URL: http://arxiv.org/abs/2402.01709v1
• Date: Thu, 25 Jan 2024 12:55:27 GMT
• Title: Toward Finding and Supporting Struggling Students in a Programming Course with an Early Warning System
• Authors: Belinda Schantong, Dominik Gorgosch, Janet Siegmund
• Abstract summary: We assess different cognitive skills of students of an introductory programming course. Most of the cognitive skills can predict whether students acquire programming skills to a certain degree. We found a significant positive effect of the syntax drill-and-practice exercises on the success of a course.
• Score: 1.192436948211501
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Background: Programming skills are advantageous to navigate today's society, so it is important to teach them to students. However, failure rates for programming courses are high, and especially students who fall behind early in introductory programming courses tend to stay behind. Objective: To catch these students as early as possible, we aim to develop an early warning system, so we can offer the students support, for example, in the form of syntax drill-and-practice exercises. Method: To develop the early warning system, we assess different cognitive skills of students of an introductory programming course. On several points in time over the course, students complete tests that measure their ability to develop a mental model of programming, language skills, attention, and fluid intelligence. Then, we evaluated to what extent these skills predict whether students acquire programming skills. Additionally, we assess how syntax drill-and-practice exercises improve how students acquire programming skill. Findings: Most of the cognitive skills can predict whether students acquire programming skills to a certain degree. Especially the ability to develop an early mental model of programming and language skills appear to be relevant. Fluid intelligence also shows predictive power, but appears to be comparable with the ability to develop a mental model. Furthermore, we found a significant positive effect of the syntax drill-and-practice exercises on the success of a course. Implications: Our first suggestion of an early warning system consists of few, easy-to-apply tests that can be integrated in programming courses or applied even before a course starts. Thus, with the start of a programming course, students who are at high risk of failing can be identified and offered support, for example, in the form of syntax drill-and-practice exercises to help students to develop programming skills.

Related papers

• Evaluating Contextually Personalized Programming Exercises Created with Generative AI [4.046163999707179]
  This article reports on a user study conducted in an elective programming course that included contextually personalized programming exercises created with GPT-4. The results demonstrate that the quality of exercises generated with GPT-4 was generally high. This suggests that AI-generated programming problems can be a worthwhile addition to introductory programming courses.
  arXiv  Detail & Related papers  (2024-06-11T12:59:52Z)
• Tapping into the Natural Language System with Artificial Languages when Learning Programming [7.5520627446611925]
  The goal of this study is to investigate the feasibility of this idea, such that we can enhance learning programming by activating language learning mechanisms. We observed that the training of the artificial language can be easily integrated into our curriculum. However, within the context of our study, we did not find a significant benefit for programming competency when students learned an artificial language first.
  arXiv  Detail & Related papers  (2024-01-12T07:08:55Z)
• Personalization, Cognition, and Gamification-based Programming Language Learning: A State-of-the-Art Systematic Literature Review [0.13053649021965597]
  Programming courses in computing science are important because they are often the first introduction to computer programming for many students. The current teacher-lecturer model of learning commonly employed in university lecture halls often results in a lack of motivation and participation in learning. This paper provides insights into designing and implementing effective personalized gamification interventions in programming courses.
  arXiv  Detail & Related papers  (2023-09-05T05:14:23Z)
• Thinking beyond chatbots' threat to education: Visualizations to elucidate the writing and coding process [0.0]
  The landscape of educational practices for teaching and learning languages has been predominantly centered around outcome-driven approaches. The recent accessibility of large language models has thoroughly disrupted these approaches. This work presents a new set of visualization tools to summarize the inherent and taught capabilities of a learner's writing or programming process.
  arXiv  Detail & Related papers  (2023-04-25T22:11:29Z)
• Leveraging Large Language Model and Story-Based Gamification in Intelligent Tutoring System to Scaffold Introductory Programming Courses: A Design-Based Research Study [6.773393436953262]
  This study explores how large language models and. gamblers can scaffold coding learning and increase. Chinese students sense of belonging in introductory programming courses.
  arXiv  Detail & Related papers  (2023-02-25T04:07:03Z)
• Generation Probabilities Are Not Enough: Uncertainty Highlighting in AI Code Completions [54.55334589363247]
  We study whether conveying information about uncertainty enables programmers to more quickly and accurately produce code. We find that highlighting tokens with the highest predicted likelihood of being edited leads to faster task completion and more targeted edits.
  arXiv  Detail & Related papers  (2023-02-14T18:43:34Z)
• ProtoTransformer: A Meta-Learning Approach to Providing Student Feedback [54.142719510638614]
  In this paper, we frame the problem of providing feedback as few-shot classification. A meta-learner adapts to give feedback to student code on a new programming question from just a few examples by instructors. Our approach was successfully deployed to deliver feedback to 16,000 student exam-solutions in a programming course offered by a tier 1 university.
  arXiv  Detail & Related papers  (2021-07-23T22:41:28Z)
• Actionable Models: Unsupervised Offline Reinforcement Learning of Robotic Skills [93.12417203541948]
  We propose the objective of learning a functional understanding of the environment by learning to reach any goal state in a given dataset. We find that our method can operate on high-dimensional camera images and learn a variety of skills on real robots that generalize to previously unseen scenes and objects.
  arXiv  Detail & Related papers  (2021-04-15T20:10:11Z)
• Mastering Rate based Curriculum Learning [78.45222238426246]
  We argue that the notion of learning progress itself has several shortcomings that lead to a low sample efficiency for the learner. We propose a new algorithm, based on the notion of mastering rate, that significantly outperforms learning progress-based algorithms.
  arXiv  Detail & Related papers  (2020-08-14T16:34:01Z)
• The ILASP system for Inductive Learning of Answer Set Programs [79.41112438865386]
  Our system learns Answer Set Programs, including normal rules, choice rules and hard and weak constraints. We first give a general overview of ILASP's learning framework and its capabilities. This is followed by a comprehensive summary of the evolution of the ILASP system.
  arXiv  Detail & Related papers  (2020-05-02T19:04:12Z)
• Emergent Real-World Robotic Skills via Unsupervised Off-Policy Reinforcement Learning [81.12201426668894]
  We develop efficient reinforcement learning methods that acquire diverse skills without any reward function, and then repurpose these skills for downstream tasks. We show that our proposed algorithm provides substantial improvement in learning efficiency, making reward-free real-world training feasible. We also demonstrate that the learned skills can be composed using model predictive control for goal-oriented navigation, without any additional training.
  arXiv  Detail & Related papers  (2020-04-27T17:38:53Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.