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

7 papers

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.SI2022★ 3 cited

Feedback Exchange and Online Affinity: A Case Study of Online Fanfiction Writers

Ruijia Cheng, Jenna Frens

Feedback is a critical piece of the creative process. Prior CSCW research has invented peer-based and crowd-based systems that exchange feedback between online strangers at scale.…

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.CL2022

Towards Robust and Semantically Organised Latent Representations for Unsupervised Text Style Transfer

Sharan Narasimhan, Suvodip Dey, Maunendra Sankar Desarkar

Recent studies show that auto-encoder based approaches successfully perform language generation, smooth sentence interpolation, and style transfer over unseen attributes using unla…

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…