paperbot · PL 论文追踪

全部论文 待读 收藏

P2 An Empirical Study of Anonymous, Unmoderated, and Online Peer-to-Peer Programming Tutoring Conversations

匿名、无主持、在线点对点编程辅导对话的实证研究
ICSE Proceedings of the IEEE/ACM 48th International Conference on Software Engineering2026匹配度 1/10 · 该论文研究匿名无主持的P2P编程辅导对话与满意度,属于CS教育/HCI方向,与用户关注的静态分析、LLM/Agent、浮点程序分析、贝叶斯程序分析等核心方向几乎没有交集。仅标签“编程环境与开发者工具”与编程工具略有关联,但不涉及PL与AI交叉。引用 1 inbox
Priscila Santiesteban, Emma Shedden, Madeline Endres, Westley Weimer
crossref: 2026-09-12

AI 速览

一句话:对108场匿名无主持P2P编程辅导对话进行混合分析,揭示其对话动态与满意度,为可扩展同伴辅导系统设计提供依据。

许多人想学编程却缺乏传统课堂指导,而Stack Overflow、ChatGPT等在线工具可能缺乏个性或强化不良开发习惯。匿名点对点(P2P)辅导有望提供可扩展支持,但尚不清楚如何为CS教育有效设计。本文对Python Tutor平台上108场匿名、无主持的点对点CS辅导会话进行混合方法分析:新手(Learner)在共享编码环境中向志愿者(Helper)求助。研究提出基于质性证据的用户动机、对话动态与学习者满意度模型。结果显示,59%的辅导交互获得有用帮助,78%的消息低毒性,无需主持即可运转;83%的对话反映软件开发关键阶段,17%的对话建立了个人联系。作者识别了与满意度相关的行为,并讨论了对可扩展同伴辅导系统设计的启示。

问题
在线学习编程缺乏可扩展的个性化支持;匿名P2P辅导虽有潜力,但尚缺乏对其用于CS教育的有效理解。
方法
对Python Tutor平台上108场匿名、无主持的文本辅导对话进行混合方法分析,建立用户动机、对话动态与学习者满意度的质性支撑模型。
评估
通过定量统计与质性编码分析对话:59%的辅导交互获得有用帮助,78%的消息低毒性,83%的对话反映软件开发过程,17%建立个人联系,并识别与满意度相关的行为。
原文摘要(Abstract)

Many people want to learn to program but lack access to traditional classroom instruction. Teaching these novices at scale is crucial for building a more diverse and capable software engineering workforce. While online tools like Stack Overflow and ChatGPT offer help, they can be impersonal or reinforce poor software development practices. Anonymous peer-to-peer (P2P) tutoring has the potential to be an additional place for scalable support, but we lack a firm understanding of how to best support it for CS pedagogy. We present a mixed-analysis study of n=108 anonymous, unmoderated P2P CS tutoring sessions. We analyze text-based conversations from Python Tutor, a widely-used learning platform. In this setting, novice programmers (Learners) request help from volunteer programmers (Helpers) in a shared coding environment. We present a qualitatively-backed model of user motivations, conversational dynamics, and Learner-reported satisfaction. Surprisingly, Learners often receive useful (\(59\%\) of tutoring interactions), low-toxicity (\(78\%\) of messages) help without moderation. P2P chats reflect key phases of the software development process (\(83\%\) of chats) and occasionally foster personal connection (\(17\%\) of chats). We identify behaviors linked to satisfaction and discuss implications for scalable peer tutoring system design for CS education.

链接与引用

DOI 原文 · PDF(开放获取) · DBLP

BibTeX
@inproceedings{SantiestebanSEW26,
  title = {An Empirical Study of Anonymous, Unmoderated, and Online Peer-to-Peer Programming Tutoring Conversations},
  author = {Priscila Santiesteban and Emma Shedden and Madeline Endres and Westley Weimer},
  booktitle = {ICSE},
  year = {2026},
  doi = {10.1145/3786580.3786958}
}