Preregistration: Prompt crafting in AI-assisted project-based learning: Effects on fifth graders' persuasive writing and the moderating role of computational thinking

This document is the preregistration of a quasi-experimental study on AI-assisted writing instruction in primary school. It was registered before any data were collected; data collection is planned for January–February 2027. The study examines whether project-based learning (PjBL) with AI-assisted prompt crafting improves Grade 5 students’ persuasive writing compared with PjBL without AI, and whether students’ computational thinking (CT) moderates this effect. In the experimental condition, students translate their persuasive arguments into prompts for an AI video generator and revise them based on the resulting videos; in the control condition, students revise hand-made storyboards. Two intact classes (N = 45) complete the competent Computational Thinking test and a persuasive writing pretest and posttest. Data will be analysed with a 2 × 2 (condition × CT level) ANCOVA controlling for pretest scores, complemented by a moderated regression with CT as a continuous variable. The document specifies the hypotheses, design, measures, exclusion criteria, and analysis plan.

Authors

Institutions

Publication Details

Journal
Zenodo (CERN European Organization for Nuclear Research)
Published
2026-11-18
DOI
https://doi.org/10.5281/zenodo.24345933
Primary Topic
Problem and Project Based Learning
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

Preregistration: Prompt crafting in AI-assisted project-based learning: Effects on fifth graders' persuasive writing and the moderating role of computational thinking

Alim Sumarno, Mustaji Mustaji, Syarah Nur Sabrina
2 links
Zenodo (CERN European Organization for Nuclear Research)
Problem and Project Based Learning
preprint

Preregistration: Prompt crafting in AI-assisted project-based learning: Effects on fifth graders' persuasive writing and the moderating role of computational thinking

Alim Sumarno, Mustaji Mustaji, Syarah Nur Sabrina
preprint en

Abstract

This document is the preregistration of a quasi-experimental study on AI-assisted writing instruction in primary school. It was registered before any data were collected; data collection is planned for January–February 2027. The study examines whether project-based learning (PjBL) with AI-assisted prompt crafting improves Grade 5 students’ persuasive writing compared with PjBL without AI, and whether students’ computational thinking (CT) moderates this effect. In the experimental condition, students translate their persuasive arguments into prompts for an AI video generator and revise them based on the resulting videos; in the control condition, students revise hand-made storyboards. Two intact classes (N = 45) complete the competent Computational Thinking test and a persuasive writing pretest and posttest. Data will be analysed with a 2 × 2 (condition × CT level) ANCOVA controlling for pretest scores, complemented by a moderated regression with CT as a continuous variable. The document specifies the hypotheses, design, measures, exclusion criteria, and analysis plan.

Zenodo (CERN European Organization for Nuclear Research)
Universitas Negeri Surabaya (ID)
Quality education
Problem and Project Based Learning
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon