检索结果-内蒙古大学图书馆

7th Conference on Learning at Scale

作者： Kovalkov, Anastasia Segal, Avi Gal, Kobi Ben Gurion Univ Negev Beer Sheva Israel Univ Edinburgh Edinburgh Midlothian Scotland

ISBN: (纸本)9781450379519

This paper explores the use of data analytics for identifying creativity in visual programming. visual programming environments are increasingly included in the schools curriculum. Their potential for promoting creative thinking in students is an important factor in their adoption. However, there does not exist a standard approach for detecting creativity in students' programming behavior, and analyzing programs manually requires human expertise and is time consuming. This work provides a computational tool for measuring creativity in visual programming that combines theory from the literature with data mining approaches. It adapts classical dimensions of creative processes to our setting, and considers new aspects such as visual elements of the visual programming projects. We apply our approach to the Scratch programming environment, measuring the creativity score of hundreds of projects. We show a preliminary comparison between our metrics and teacher ratings.

关键词： Creativity Creativity Tests visual programming environments

来源：评论

学校读者我要写书评

暂无评论

NextBlocks: An Interactive Block programming Platform 29

NextBlocks: An Interactive Block Programming Platform

引用

29th Annual Conference on Innovation and Technology in Computer Science Education (ITiCSE)

作者： Pereira, Duarte Barbosa, Fernanda Morgado, Carmen Nova Sch Sci & Technol Dept Comp Sci Caparica Setubal Portugal

ISBN: (纸本)9798400706004

Since Seymour Papert's work with the Logo programming language in the 1960s, there has been a prevailing belief in the effectiveness of visual programming environments for teaching programming to children and novices. As these platforms evolved and became more prevalent, using block programming to teach children and beginners became increasingly more common. However, modern block programming platforms like Scratch and *** excessively restrict educators by not allowing them to create custom exercises in the platform. They also tend to make programming a solo activity, not allowing for collaboration and cooperation between learners (Scratch is an exception in this regard). Additionally, they are usually located in standalone websites instead of being implemented in locations that students already frequent regularly. Having identified these gaps in the field of block programming environments, this paper proposes NextBlocks, a new block programming platform implemented as a Moodle plugin. This platform enables educators to create custom exercises, emphasizing social perception and collaboration features. It supports features that are uncommon in block programming environments, contributing to a more interactive and engaging learning experience. Furthermore, being integrated into the Moodle Learning Management System makes NextBlocks more easily accessible within the educational framework. As an open-source platform, besides solving current challenges, it can also serve as a foundation for future expansion by the education community. This paper explores some of the unique features of NextBlocks, presents a case study on the platform, and discusses its potential contributions to enhancing programming education for beginners within a collaborative learning environment.

关键词： visual programming environments Block programming Moodle Computer Science Education Social Perception and Collaboration

来源：评论

学校读者我要写书评

暂无评论

ChainForge: A visual Toolkit for Prompt Engineering and LLM Hypothesis Testing 24

ChainForge: A Visual Toolkit for Prompt Engineering and LLM ...

引用

CHI Conference on Human Factors in Computing Sytems (CHI)

作者： Arawjo, Ian Swoopes, Chelse Vaithilingam, Priyan Wattenberg, Martin Glassman, Elena L. Harvard Univ SEAS Cambridge MA 02138 USA Harvard Univ Insight & Interact Lab Cambridge MA USA

ISBN: (纸本)9798400703300

Evaluating outputs of large language models (LLMs) is challenging, requiring making-and making sense of-many responses. Yet tools that go beyond basic prompting tend to require knowledge of programming APIs, focus on narrow domains, or are closed-source. We present ChainForge, an open-source visual toolkit for prompt engineering and on-demand hypothesis testing of text generation LLMs. ChainForge provides a graphical interface for comparison of responses across models and prompt variations. Our system was designed to support three tasks: model selection, prompt template design, and hypothesis testing (e.g., auditing). We released ChainForge early in its development and iterated on its design with academics and online users. Through in-lab and interview studies, we find that a range of people could use ChainForge to investigate hypotheses that matter to them, including in real-world settings. We identify three modes of prompt engineering and LLM hypothesis testing: opportunistic exploration, limited evaluation, and iterative refinement.

关键词： language models toolkits visual programming environments prompt engineering auditing

来源：评论

学校读者我要写书评

暂无评论

ChainBuddy: An AI-assisted Agent System for Generating LLM Pipelines 25

ChainBuddy: An AI-assisted Agent System for Generating LLM P...

引用

2025 CHI Conference on Human Factors in Computing Systems, CHI 2025

作者： Zhang, Jingyue Arawjo, Ian Montréal HCI Université de Montréal Montréal QC Canada

ISBN: (纸本)9798400713941

As large language models (LLMs) advance, their potential applications have grown significantly. However, it remains difficult to evaluate LLM behavior on user-defined tasks and craft effective pipelines to do so. Many users struggle with where to start, often referred to as the "blank page problem."ChainBuddy, an AI workflow generation assistant built into the ChainForge platform, aims to tackle this issue. From a single prompt or chat, ChainBuddy generates a starter evaluative LLM pipeline in ChainForge aligned to the user's requirements. ChainBuddy offers a straightforward and user-friendly way to plan and evaluate LLM behavior and make the process less daunting and more accessible across a wide range of possible tasks and use cases. We report a within-subjects user study comparing ChainBuddy to the baseline interface. We find that when using AI assistance, participants with a variety of technical expertise reported a less demanding workload, felt more confident, and produced higher quality pipelines evaluating LLM behavior. However, we also uncover a mismatch between subjective and objective ratings of performance: participants rated their successfulness similarly across conditions, while independent experts rated participant workflows significantly higher with AI assistance. Drawing connections to the Dunning-Kruger effect, we discuss implications for the future design of workflow generation assistants regarding the risk of over-reliance. © 2025 Copyright held by the owner/author(s). Publication rights licensed to ACM.

关键词： AI agents automation language models LLM pipelines prompt engineering visual programming environments

来源：评论

学校读者我要写书评

暂无评论

G4D-a treasure hunt game for novice programmers to learn debugging

引用

SMART LEARNING environments 2020年第1期7卷 1-21页

作者： Venigalla, Akhila Sri Manasa Chimalakonda, Sridhar Indian Inst Technol Dept Comp Sci & Engn Res Intelligent Software & Human Analyt RISHA Lab Tirupati Andhra Pradesh India

visual programming environments (VPEs) are predominantly being used to teach programming concepts through interactive games with interesting narratives. Games have been developed to teach basic concepts of programming such as deriving logic, writing code, debugging the code and so on. Debugging code is one of the most important activities that can improve the skill of tackling a problem. In programming, one needs to identify the correct location of an error and fix it, which is usually learned through experience. Games have been developed to teach debugging to novice programmers. Syntactical errors occur frequently in the early stages of programming. The existing debugging games aim to support users in debugging the logic of the problem, but do not target on correcting the code snippets based on syntax. To address this challenge of providing syntactical support, we propose a treasure hunt based debugging game, in which users pass through various levels of the game by debugging code snippets written in C language. We have evaluated G4D based on MEEGA+ model, with 20 volunteers, having different programming backgrounds. The results of the user survey indicate that G4D has a good quality level and about 75% of the volunteers have either strongly agreed or agreed to recommend G4D to their colleagues.

关键词： Learning technologies visual programming environments Novice programmers Debugging games

来源：评论

学校读者我要写书评

暂无评论

Node and Block-Based Development Tools for Distributed Systems With AI Applications

引用

IEEE ACCESS 2019年 7卷 143109-143119页

作者： Hauck, Marcel Machhamer, Rudiger Czenkusch, Levin Gollmer, Klaus-Uwe Dartmann, Guido Mainz Univ Appl Sci Res Grp Business Informat & Media Management D-55128 Mainz Germany Trier Univ Appl Sci Inst Software Syst Environm Campus Birkenfeld D-55761 Birkenfeld Germany

Internet of Things (IoT) and Artificial Intelligence (AI) are one of the most promising and disruptive areas of current research and development. However, these areas require deep knowledge in multiple disciplines such as sensors, protocols, embedded programming, distributed systems, statistics and algorithms. This broad knowledge is not easy to acquire and the software used to design these systems is becoming increasingly complex. Small and medium-sized enterprises therefore have problems in developing new business ideas. However, node- and block-based software tools have also been released and are freely available as open source toolboxes. In this paper, we present an overview of multiple node- and block-based software tools to develop IoT- and AI-based business ideas. We arrange these tools according their capabilities and further propose extension and combinations of tools to design a useful open-source library for small and medium-sized enterprises, that is easy to use and helps with rapid prototyping, enabling new business ideas to be developed using distributed computing.

关键词： Distributed computing Internet of Things machine learning rapid prototyping visual programming environments

来源：评论

学校读者我要写书评

暂无评论

The Effectiveness Of Codesters In Teaching Basic Computer Science Topics

The Effectiveness Of Codesters In Teaching Basic Computer Sc...

引用

作者： Antonio Pedro Moctezuma University of Wisconsin – Milwaukee

学位级别：硕士

Founded in 2014, Codesters is a visual programming environment (VPE) like the popular Scratch and Alice. Its goal is to teach middle school and older studentâs computer programming. Unlike its predecessors, users of Codesters drag and drop actual Python code instead of blocks and can edit the code themselves. Codesters has also developed modules that integrate coding lessons into the VPE. In this study, we consider the Codesters Python 1 module and investigate its effectiveness in teaching the basic coding concepts of variables, loops and conditionals. During Fall 2018 and Spring 2019, we ran a coding class for eighth graders at a local Milwaukee school based on this module. We gave a pre-test, three quizzes and a post-test to evaluate what the students have learned. We then analyzed the results of these evaluations and compared them to those taken by students who learned programming in a traditional CS1 class. Our results indicate that users of Codesters understood loops and conditionals as well as the students from the traditional CS1 class. We also found that the pre-test was a poor indicator of studentsâ performance in the coding class suggesting that Codesters is able to engage students who might not necessarily excel in a traditional classroom.

关键词： Block programming Codesters K-12 Education visual programming environments visual programming Languages Education Other Education

来源：评论

学校读者我要写书评

暂无评论

Iconic framework for cooperative coding 18

Iconic framework for cooperative coding

引用

19th Bulgarian International Conference on Computer Systems and Technologies (CompSysTech)

作者： Averna, Guido Lenzitti, Biagio Taibi, Davide Tegolo, Domenico Dept Maths & Comp Sci Palermo PA Italy CNR Palermo PA Italy

ISBN: (纸本)9781450364256

The description of an innovative framework built on top of Web based visual programming environment is the primary aim of this contribution. In the last decade, many frameworks oriented to visual languages have been introduced in literature to improve the skill on programming languages, but at the best of our knowledge, no framework has been specially designed to support collaborative work on heterogeneous distributed environments. Therefore, SIRENE introduces a new framework in which beginners and experts can cooperate to develop algorithms by using a visual and iconic paradigm. Students, in the classroom or connected from everywhere, can he involved into the definition of the algorithm, can asynchronously modify the common working space, show a visual function to expert, thus the server hosts a shared space in which the algorithms can be visualised and modified by all of the SIRENE clients. SIRENE is primarily a visual framework oriented to collaborative approaches in which each user can visualise the evolution or implementation of some algorithms and modify it during its development by other users.

关键词： Application programming Interfaces Collaborative Coding visual programming environments Web-based Iconic Interface Interactive learning control

来源：评论

学校读者我要写书评

暂无评论

Mining Sequential Patterns to Explore Users' Learning Behavior in a visual programming App 42

Mining Sequential Patterns to Explore Users' Learning Behavi...

引用

42nd Annual IEEE-Computer-Society Computers, Software and Applications (COMPSAC) Conference - Staying Smarter in a Smartening World

作者： Shih, Wen-Chung Asia Univ Dept Comp Sci & Informat Engn Taichung Taiwan

ISBN: (纸本)9781538626672

visual programming environments combined with problem-solving are useful for promoting students' motivation of learning programming. The purpose of this work is to use a blockly visual programming educational app for university students and analyze their learning behavior patterns. The study uses a sequential pattern mining tool to mine the students' behavioral patterns. The preliminary results showed that the proposed method can find behavior patterns of high-achievement students and low-achievement students.

关键词： sequential pattern mining visual programming environments educational app learning behavior

来源：评论

学校读者我要写书评

暂无评论

Mining Learners' Behavioral Sequential Patterns in a Blockly visual programming Educational Game

Mining Learners' Behavioral Sequential Patterns in a Blockly...

引用

International Conference on Industrial Engineering, Management Science and Application (ICIMSA)

作者： Shih, Wen-Chung Asia Univ Dept Comp Sci & Informat Engn Taichung Taiwan

ISBN: (纸本)9781509063352

Previous researches have claimed that visual programming environments are helpful for learning programming by problem-solving. The purpose of this work is to use a blockly visual programming educational game for university students and analyze their sequential learning behaviors. The study presented a two-level sequential pattern mining algorithm to mine the students' behavioral patterns.

关键词： sequential pattern mining visual programming environments educational games learners' behavior

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：