Despite extensive research on code plagiarism detection in higher education and for programming languages like Java and Python, limited work has focused on K-12 settings, particularly for pseudocode. This study aims t...
详细信息
ISBN:
(纸本)9798400705311
Despite extensive research on code plagiarism detection in higher education and for programming languages like Java and Python, limited work has focused on K-12 settings, particularly for pseudocode. This study aims to address this gap by building explainable machine learning models for pseudocode plagiarism detection in online programming education. To achieve this, we construct a comprehensive dataset comprising 7,838 pseudocode submissions from 2,578 high school students enrolled in an online programming foundations course, along with 6,300 pseudocode samples generated by three versions of generative pre-trained transformer (GPT) models. Utilizing this dataset, we develop an explainable model to detect AI-generated pseudocode across various assessments. The model not only identifies AI-generated content but also provides insights into its predictions at both the student and problem levels, thus enhancing our understanding of AI-generated pseudocode in K-12 education. Furthermore, we analyzed SHAP values and key features of the model to pinpoint student submissions that closely resemble AI-generated pseudocode. This research offers implications for developing robust educational technologies and methodologies to uphold academic integrity in online programming courses.
programming is an essential skill in computerscience and in a wide range of engineering-related disciplines. However, occurring errors, often referred to as "bugs" in code, can indeed be challenging to iden...
详细信息
programming is an essential skill in computerscience and in a wide range of engineering-related disciplines. However, occurring errors, often referred to as "bugs" in code, can indeed be challenging to identify and rectify, both for students who are learning to program and for experienced professionals. These errors can lead to unexpected behaviors in programming. Understanding, finding, and effectively dealing with errors is an integral part of programming learning as well as software development. To classify the errors, we propose a multi-label error classification of source code for dealing with programming data by using the ML-KNN classifier with CodeT5 embeddings. In addition, several deep neural network (DNN) models, including GRU, LSTM, BiLSTM, and BiLSTM-A (attention mechanism) are also employed as baseline models to classify the errors. We trained all the models by using a large-scale dataset (original error labels) as well as modified datasets (summarized error labels) of the source code. The average classification accuracy of the proposed model is 95.91% and 84.77% for the original and summarized error-labeled datasets, respectively. The exact match accuracy is 22.57% and 27.22% respectively for the original and summarized error-labeled datasets. The comprehensive experimental results of the proposed approach are promising for multi-label error classification over the baseline models. Moreover, the findings derived from the proposed approach and data-driven analytical results hold significant promise for error classification, programming education, and related research endeavors.
Graph neural networks (GNNs) have gained significant popularity due to the powerful capability to extract useful representations from graph data. As the need for efficient GNN computation intensifies, a variety of pro...
详细信息
Graph neural networks (GNNs) have gained significant popularity due to the powerful capability to extract useful representations from graph data. As the need for efficient GNN computation intensifies, a variety of programming abstractions designed for optimizing GNN Aggregation have emerged to facilitate acceleration. However, there is no comprehensive evaluation and analysis upon existing abstractions, thus no clear consensus on which approach is better. In this letter, we classify existing programming abstractions for GNN Aggregation by the dimension of data organization and propagation method. By constructing these abstractions on a state-of-the-art GNN library, we perform a thorough and detailed characterization study to compare their performance and efficiency, and provide several insights on future GNN acceleration based on our analysis.
We propose a decomposition algorithm for multistage stochastic programming that resembles the progressive hedging method of Rockafellar and Wets but is provably capable of several forms of asynchronous operation. We d...
详细信息
We propose a decomposition algorithm for multistage stochastic programming that resembles the progressive hedging method of Rockafellar and Wets but is provably capable of several forms of asynchronous operation. We derive the method from a class of projective operator splitting methods fairly recently proposed by Combettes and Eckstein, significantly expanding the known applications of those methods. Our derivation assures convergence for convex problems whose feasible set is compact, subject to some standard regularity conditions and a mild "fairness" condition on subproblem selection. The meth-od's convergence guarantees are deterministic and do not require randomization, in con-trast to other proposed asynchronous variations of progressive hedging. Computational experiments described in an online appendix show the method to outperform progressive hedging on large-scale problems in a highly parallel computing environment.
Technologies permeate contemporary society, and the ability to use computerscience concepts in problem-solving is essential to everyone. This paper presents an epistemic tool of semiotic engineering whose meaning is ...
详细信息
Technologies permeate contemporary society, and the ability to use computerscience concepts in problem-solving is essential to everyone. This paper presents an epistemic tool of semiotic engineering whose meaning is resignified to the context of teaching programming to initial learners. Aiming to help these students absorb programming concepts, we structured a gradual form of presentation using the interaction with a new system as a journey through a new culture, based on the Cultural Viewpoint Metaphors theory. After that, we applied this resignification in an introductory programming workshop using visual programming and the BBC Micro:bit embedded device. Results from the workshop revealed that this gradual introduction could help novices in the programming concepts learning process, showing the potential of this approach in teaching programming.
Dr Barbara Liskov - a mostly retired Institute Professor at the Massachusetts Institute of Technology, a pioneer in object-oriented programming and distributed systems and the winner of the 2008 ACM A. M. Turing Award...
Dr Barbara Liskov - a mostly retired Institute Professor at the Massachusetts Institute of Technology, a pioneer in object-oriented programming and distributed systems and the winner of the 2008 ACM A. M. Turing Award, which is the highest distinction in computerscience - talks to Nature Computational science about her work on data abstractions, her career trajectory and recognizing the contributions of women in computerscience.
Computational thinking, as an essential competency for the future development of citizens, is an important goal of computerscience instruction. Although studies have shown that early exposure to computerprogramming ...
详细信息
Computational thinking, as an essential competency for the future development of citizens, is an important goal of computerscience instruction. Although studies have shown that early exposure to computerprogramming is beneficial for improving computational thinking, current programming instruction does not systematically consider the factors that influence the development of computational thinking. To promote the early development of computational thinking, we analyzed the main factors that influence the development of computational thinking in terms of learners' cognitive level, instructional content, and technological environment. Therefore, this study proposes a teaching framework for developing computational thinking based on embodied cognitive theory. This teaching framework shows how to choose a suitable technological environment, design the appropriate content and apply adequate methods to effectively promote students' computational thinking development.
In this poster, we report our on-going project that aims to design a good set of course materials for introduction to programming using a functional programming language, Clean[2]. While procedural languages such as C...
详细信息
ISBN:
(纸本)9798400701399
In this poster, we report our on-going project that aims to design a good set of course materials for introduction to programming using a functional programming language, Clean[2]. While procedural languages such as C, Python, etc are used in most introduction to programming classes, we believe that Clean might be better for students, because the syntax is very simple and in many cases, the size of a program in Clean is shorter than a corresponding program in C or other procedural languages. In addition, if Clean is used in an introduction to programming course, a lot of recursive examples can be introduced intuitively. This is important because even though recursion is one of important concepts that students should understand, many students have difficulty understanding the concept[3].
The integration of large language models (LLMs) into educational settings represents a significant technological breakthrough, offering substantial opportunities alongside profound ethical challenges. Higher education...
详细信息
The integration of large language models (LLMs) into educational settings represents a significant technological breakthrough, offering substantial opportunities alongside profound ethical challenges. Higher education institutions face the widespread use of these tools by students, requiring them to navigate complex decisions regarding their adoption. This includes determining whether to allow the use of LLMs, defining their appropriate scope, and establishing guidelines for their responsible and ethical application. In the context of computerscience education, these challenges are particularly acute. On the one hand, the capabilities of LLMs significantly enhance the tools available to developers and software engineers. On the other hand, students' over-reliance on LLMs risks hindering their development of foundational skills. This study examines these challenges and proposes strategies to regulate the use of LLMs while upholding academic integrity. It focuses on the specific impact of LLMs in programming education, where dependence on AI-generated solutions may erode active learning and essential skill acquisition. Through a comprehensive literature review and drawing on teaching experience and guidelines from global institutions, this study contributes to the broader discourse on the integration of these advanced technologies into educational environments. The goal is to enhance learning outcomes while ensuring the development of competent, ethical software professionals.
There are a wide variety of intelligence accelerators with promising performance and energy efficiency,deployed in a broad range of applications such as computer vision and speech ***,programming productivity hinders ...
详细信息
There are a wide variety of intelligence accelerators with promising performance and energy efficiency,deployed in a broad range of applications such as computer vision and speech ***,programming productivity hinders the deployment of deep learning *** low-level library invoked in the high-level deep learning framework which supports the end-to-end execution with a given model,is designed to reduce the programming burden on the intelligence ***,it is inflexible for developers to build a network model for every deep learning application,which probably brings unnecessary repetitive *** this paper,a flexible and efficient programming framework for deep learning accelerators,FlexPDA,is proposed,which provides more optimization opportunities than the low-level library and realizes quick transplantation of applications to intelligence accelerators for fast *** evaluate FlexPDA by using 10 representative operators selected from deep learning algorithms and an end-to-end *** experimental results validate the effectiveness of FlexPDA,which achieves an end-to-end performance improvement of 1.620x over the low-level library.
暂无评论