一句话：通过文献综述提炼 ML 终端用户程序员的挑战与支持策略，设计对话代理 Newton 并经用户研究验证其有效性。
论文关注缺乏背景的机器学习终端用户程序员（ML-EUP）在学习曲线陡峭、模型易错等方面的困难。作者先通过文献综述识别出 ML-EUP 面临的六项主要挑战和五项支持策略，并据此设计对话代理 Newton，使其扮演专家角色提供协助。评估采用 Wizard of Oz 被试内研究，12 名 ML-EUP 参与。结果表明 Newton 能有效帮助参与者应对文献所列挑战；作者进一步提出六条对话代理设计指南，可迁移到其他终端用户编程应用和软件工程活动。
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.
@inproceedings{paperbot11458,
title = {How to Support ML End-User Programmers through a Conversational Agent},
author = {Emily Judith Arteaga Garcia and João Felipe Nicolaci Pimentel and Zixuan Feng and Marco Gerosa and Igor Steinmacher and Anita Sarma},
booktitle = {ICSE},
year = {2024},
doi = {10.1145/3597503.3608130}
}