most citedInvestigating and Designing for Trust in AI-powered Code Generation Tools

79 citations · 117 across the 7 of their papers we have counts for

collaborators
Showing cs.HCShow all

5 papers · 1 filter

cs.HC2023★ 79 cited

Investigating and Designing for Trust in AI-powered Code Generation Tools

Ruotong Wang, Ruijia Cheng, Denae Ford +1

As AI-powered code generation tools such as GitHub Copilot become popular, it is crucial to understand software developers' trust in AI tools -- a key factor for tool adoption and…

cs.HC2022★ 7 cited

"It would work for me too": How Online Communities Shape Software Developers' Trust in AI-Powered Code Generation Tools

Ruijia Cheng, Ruotong Wang, Thomas Zimmermann +1

While revolutionary AI-powered code generation tools have been rising rapidly, we know little about how and how to help software developers form appropriate trust in those AI tools…

cs.HC2022★ 10 cited

Many Destinations, Many Pathways: A Quantitative Analysis of Legitimate Peripheral Participation in Scratch

Ruijia Cheng, Benjamin Mako Hill

Although informal online learning communities have proliferated over the last two decades, a fundamental question remains: What are the users of these communities expected to learn…

cs.HC2022★ 4 cited

Mapping the Design Space of Human-AI Interaction in Text Summarization

Ruijia Cheng, Alison Smith-Renner, Ke Zhang +2

Automatic text summarization systems commonly involve humans for preparing data or evaluating model performance, yet, there lacks a systematic understanding of humans' roles, exper…

cs.HC2022★ 14 cited

How Interest-Driven Content Creation Shapes Opportunities for Informal Learning in Scratch: A Case Study on Novices' Use of Data Structures

Ruijia Cheng, Sayamindu Dasgupta, Benjamin Mako Hill

Through a mixed-method analysis of data from Scratch, we examine how novices learn to program with simple data structures by using community-produced learning resources. First, we…