Zobrazeno 1 - 10
of 27
pro vyhledávání: '"Ericson, Barbara"'
Autor:
Padiyath, Aadarsh, Hou, Xinying, Pang, Amy, Vargas, Diego Viramontes, Gu, Xingjian, Nelson-Fromm, Tamara, Wu, Zihan, Guzdial, Mark, Ericson, Barbara
The capability of large language models (LLMs) to generate, debug, and explain code has sparked the interest of researchers and educators in undergraduate programming, with many anticipating their transformative potential in programming education. Ho
Externí odkaz:
http://arxiv.org/abs/2406.06451
CodeTailor: LLM-Powered Personalized Parsons Puzzles for Engaging Support While Learning Programming
Learning to program can be challenging, and providing high-quality and timely support at scale is hard. Generative AI and its products, like ChatGPT, can create a solution for most intro-level programming problems. However, students might use these t
Externí odkaz:
http://arxiv.org/abs/2401.12125
Novice programmers need to write basic code as part of the learning process, but they often face difficulties. To assist struggling students, we recently implemented personalized Parsons problems, which are code puzzles where students arrange blocks
Externí odkaz:
http://arxiv.org/abs/2401.03144
Computing artifacts tend to exclude marginalized students, so we must create new methods to critique and change them. We studied the potential for "satirical programming" to critique artifacts as part of culturally responsive computing (CRC) pedagogy
Externí odkaz:
http://arxiv.org/abs/2312.03090
Autor:
Kazemitabaar, Majeed, Hou, Xinying, Henley, Austin, Ericson, Barbara J., Weintrop, David, Grossman, Tovi
As Large Language Models (LLMs) gain in popularity, it is important to understand how novice programmers use them. We present a thematic analysis of 33 learners, aged 10-17, independently learning Python through 45 code-authoring tasks using Codex, a
Externí odkaz:
http://arxiv.org/abs/2309.14049
Autor:
Kazemitabaar, Majeed, Chow, Justin, Ma, Carl Ka To, Ericson, Barbara J., Weintrop, David, Grossman, Tovi
AI code generators like OpenAI Codex have the potential to assist novice programmers by generating code from natural language descriptions, however, over-reliance might negatively impact learning and retention. To explore the implications that AI cod
Externí odkaz:
http://arxiv.org/abs/2302.07427
Autor:
Ericson, Barbara1 barbarer@umich.edu
Publikováno v:
Communications of the ACM. Feb2023, Vol. 66 Issue 2, p26-29. 4p. 2 Color Photographs.
Publikováno v:
ACM International Conference Proceeding Series; 11/21/2019, p1-10, 10p
Publikováno v:
ACM International Conference Proceeding Series; 11/16/2017, p20-29, 10p
Publikováno v:
Communications of the ACM; Feb2016, Vol. 59 Issue 2, p32-34, 3p, 1 Color Photograph