evidoria

← Back to browse

Good practice Imported

ReadCraft — An AI Story-Creation Reading Intervention for Chinese Children With Dyslexia

China · Hangzhou · See the China profile · See the Hangzhou profile

Evidence: Quasi-experimental Top 40% 53/100 · Ask Evidence Copilot about this practice

A Hangzhou Dianzi University-led team built ReadCraft, letting children with dyslexia co-create illustrated stories with AI before practising reading them. A controlled study of 52 children found gains in accuracy, fluency, motivation and self-efficacy versus standard materials.

52 children
Study sample size

Details

Maturity
Pilot
Promoter
Hangzhou Dianzi University (School of Media and Design)
Period
2025–2026 (published May 2026)
Keywords
assistive technology, special education, reading intervention, human-computer interaction research

Context

Chinese children with dyslexia often face persistent difficulties with character recognition and reading fluency, and researchers note that existing digital interventions are frequently generic, poorly localised and hard to sustain outside a clinical setting.

Activities

A team based at Hangzhou Dianzi University's School of Media and Design, working with China Jiliang University, Communication University of Zhejiang, Hong Kong Polytechnic University and Cornell University, built ReadCraft around a 'Create-Read-Produce' framework, in which children first co-create an illustrated story with AI-assisted tools, then practise reading it through four graded modes from AI-mentored support to independent reading, and finally publish their own finished book.

Results

In a controlled study with 52 children, ReadCraft use was associated with significant improvements in reading accuracy, fluency, motivation and self-efficacy compared with standard reading materials, though the specific effect sizes were not accessible outside the paywalled full text.

Conclusions

As a 52-child controlled study rather than a classroom-scale deployment, ReadCraft's real-world feasibility, cost and durability at scale remain untested.

Implementation

Indicative cost
Low (< €50k)
Time to results
Short (< 1 year)
Staffing & skills
research team (Hangzhou Dianzi University School of Media and Design, with partner universities)

Conditions for success

  • AI-assisted story co-creation paired with graded reading-practice modes tailored to dyslexic readers

Common failure modes

  • small 52-child sample at a single research site; real-world classroom feasibility, cost and durability at scale untested

Where it fits

Governance type
university research project
Scale
single research study (52 children)
Income level
upper-middle-income

Commonly funded by

National / regional programmes

Indicative funding routes for practices of this type — always check each programme's current calls and eligibility rules.

Replication kit

Reusable artefacts from this practice — as published by their sources.

Do you run this practice? Claim it — verified implementers get a public contact pathway and can propose corrections.

Data sources

Where this practice's information was retrieved from, and when.

Similar practices you may find useful