How to Support ML End-User Programmers through a Conversational Agent

How to Support ML End-User Programmers through a Conversational Agent
复制标题

如何通过会话代理支持 ML 最终用户程序员

DOI:
10.1145/3597503.3608130
复制
发表时间:
2024
期刊:
Proceedings of the International Conference on Software Engineering
影响因子:
--
通讯作者:
Sarma, Anita
Sarma, Anita
中科院分区:
--
文献类型:
--
作者:
Arteaga Garcia, Emily Judith;Nicolaci Pimentel, João Felipe;Feng, Zixuan;Gerosa, Marco;Steinmacher, Igor;Sarma, Anita

文献摘要

参考文献

相似文献

机器学习 (ML) 对于最终用户程序员 (EUP) 应用程序来说越来越重要。然而,没有适当背景的机器学习最终用户程序员 (ML-EUP) 面临着令人畏惧的学习曲线以及模型中出现错误和缺陷的更高风险。在这项工作中,我们设计了一个名为“Newton”的会话代理作为支持 ML-EUP 的专家。 Newton 的设计是通过对现有文献的全面回顾而形成的,我们从中确定了 ML-EUP 面临的六大主要挑战以及五项帮助它们的策略。为了评估牛顿设计的有效性,我们使用 12 个 ML-EUP 进行了一项绿野仙踪受试者内研究。我们的研究结果表明,Newton 有效地协助了 ML-EUP,解决了文献中强调的挑战。我们还为未来的会话代理提出了六项设计指南,这可以帮助其他 EUP 应用程序和软件工程活动。
Machine Learning (ML) is increasingly gaining significance for enduser programmer (EUP) applications. However, machine learning end-user programmers (ML-EUPs) without the right background face a daunting learning curve and a heightened risk of mistakes and flaws in their models. In this work, we designed a conversational agent named "Newton" as an expert to support ML-EUPs. Newton's design was shaped by a comprehensive review of existing literature, from which we identified six primary challenges faced by ML-EUPs and five strategies to assist them. To evaluate the efficacy of Newton's design, we conducted a Wizard of Oz within-subjects study with 12 ML-EUPs. Our findings indicate that Newton effectively assisted ML-EUPs, addressing the challenges highlighted in the literature. We also proposed six design guidelines for future conversational agents, which can help other EUP applications and software engineering activities.
DOI: 10.1109/cesser-ip.2019.00009
发表时间: 2019-05
期刊: 2019 IEEE/ACM Joint 7th International Workshop on Conducting Empirical Studies in Industry (CESI) and 6th International Workshop on Software Engineering Research and Industrial Practice (SER&IP)
影响因子: --
作者:
F. Ishikawa;Nobukazu Yoshioka
通讯作者: F. Ishikawa;Nobukazu Yoshioka
DOI: 10.3390/info11070363
发表时间: 2020-07-01
期刊: INFORMATION
影响因子: 3.1
作者:
Karamitsos, Ioannis;Albarhami, Saeed;Apostolopoulos, Charalampos
通讯作者: Apostolopoulos, Charalampos
VCL自动生成代码框架的可视化和分析工具
DOI: --
发表时间: 2021
期刊: International Conference on Service Operations and Logistics, and Informatics
影响因子: --
作者:
R. Kirwan;Javihn Che;Woo Jia Le;Stefan Sarin
通讯作者: Stefan Sarin
隐性指导及其在 Apache 中的流行程度和影响的案例研究
DOI: 10.1145/3540250.3549167
发表时间: 2022
期刊: 30th ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering
影响因子: --
作者:
Feng, Zixuan;Chatterjee, Amreeta;Sarma, Anita;Ahmed, Iftekhar
通讯作者: Ahmed, Iftekhar
开放编码描述
DOI: --
发表时间: 2016
期刊:
影响因子: --
作者:
B. Glaser;Hon.
通讯作者: Hon.