English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Programming can be challenging for novices, but it is difficult to providehigh-quality, comprehensive, and timely support at scale. Generative AI and itsproducts, like ChatGPT, can create a solution for most introductory programmingproblems. However, students may become overly reliant on these tools for quickcode generation and homework completion, leading to reduced engagement andlimited learning. In this work, we present \sys{}, a system that utilizes largelanguage models (LLM) while still promoting students' cognitive engagement.\sys{} provides a personalized Parsons puzzle to support struggling students.In a Parsons puzzle, students place mixed-up code blocks in the correct orderto solve a problem. A technical evaluation with 800 incorrect student codedemonstrated that \sys{} can efficiently create high-quality (correct,personalized, and concise) Parsons puzzles for students. In a within-subjectsexperiment with 18 novice programmers, most students rated using \sys{} as moreengaging, and they preferred \sys{} for learning rather than simply receivingan AI-generated solution. Additionally, students recalled more new elementsfrom the supported practice to the posttest after using \sys{}, compared towhen they simply received a direct solution. Qualitative observations andinterviews provided evidence for the benefits of \sys{} including emphasizingalgorithmic thinking, fostering continuity in learning, promoting metacognitivereflection, and boosting student confidence. We conclude by suggesting futuredesigns for applying generative AI in a way that minimizes over-reliance andenhances learning.

CodeTailor: Personalized Parsons Puzzles are Preferred Over AI-Generated Solutions to Support Learning