Towards Designing Conversational Agents for Pair Programming: Accounting for Creativity Strategies and Conversational StylesFull paper
Established research on pair programming reveals benefits, including increasing communication, creativity and self-efficacy. However, research has reported limitations such as finding a compatible partner, scheduling sessions between partners, and resistance to pairing. Further, pairings can be affected by predispositions to negative stereotypes. These problems can be addressed by replacing one human member of the pair with a conversational agent. To investigate the design space of such a conversational agent, we conducted a controlled remote pair programming study. Our analysis found various creative problem-solving strategies and differences of conversational style. We further analyzed the transferable strategies from human-human collaboration to human-agent collaboration by conducting a Wizard of Oz study. The findings from the two studies helped us gain insights regarding the design of a programmer conversational agent. We make recommendations for researchers and practitioners for designing pair programming conversational agent tools.
Wed 12 AugDisplayed time zone: Pacific Time (US & Canada) change
12:15 - 13:00 | Supporting Learning by Novice ProgrammersResearch Papers at Zoom Room Chair(s): Caitlin Kelleher Washington University in St. Louis | ||
12:15 15mTalk | Coding Strip: A Pedagogical Tool for Teaching and Learning Programming Concepts through ComicsFull paper Research Papers Sangho Suh University of Waterloo, Martinet Lee University of Waterloo, Gracie Xia University of Waterloo, Edith Law University of Waterloo Authorizer link | ||
12:30 15mTalk | Towards Designing Conversational Agents for Pair Programming: Accounting for Creativity Strategies and Conversational StylesFull paper Research Papers Sandeep Kuttal The University of Tulsa, Jarow Myers The University of Tulsa, Sam Gurka The University of Tulsa, David Magar The University of Tulsa, David Piorkowski IBM T.J. Watson Research Center, Rachel Bellamy IBM T.J. Watson Research Center | ||
12:45 8mTalk | EdCode: Towards Personalized Support at Scale for Remote Assistance in CS EducationShort paper Research Papers Yan Chen University of Michigan, Jaylin Herskovitz University of Michigan, Gabriel Matute University of Michigan, April Wang University of Michigan, Sang Won Lee Virginia Polytechnic Institute and State University, Walter Lasecki University of Michigan, Steve Oney University of Michigan Authorizer link | ||
12:53 7mTalk | Exploring Differences Between Student and Teacher Created Snap! ProjectsShort paper Research Papers Amy Isvik North Carolina State University, Veronica Catete North Carolina State University, Lauren Alvarez North Carolina State University, Nicholas Lytle North Carolina State University, Tiffany Barnes North Carolina State University Authorizer link |