Using Matrix Training to Promote Oral WH-Syntax Production in Chinese-Speaking Autistic Children: A Human-AI Collaborative Instructional Design

Matrix training is an evidence-based approach for fostering generative language in autistic children, yet its application to high-dimensional syntactic structures remains limited by the logistical demands of stimulus preparation. This study evaluated a structured instructional protocol supported by a human-AI collaborative design process to improve the oral production of five-element WH-syntax (Who, When, Where, How, and Doing What) in 10 Chinese-speaking autistic children. Utilizing a multiple-probe design across participants, generative AI was employed under expert practitioner supervision to assist in developing a culturally adaptive 126-item instructional matrix from a theoretical universe of 162 permutations. Results indicated that all 10 participants achieved mastery criteria within an average of 8.1 instructional sessions (8 trials per session). Between-case standardized mean difference estimates indicated a substantial intervention effect size (BC-SMD = 30.33, 95% CI [27.53, 33.13]), and participants demonstrated skill transfer across novel stimulus combinations and follow-up maintenance probes. These preliminary findings suggest that human-guided AI support can reduce preparation barriers for educators, providing a feasible framework for delivering complex syntactic instruction in special education settings.

Authors

Institutions

Publication Details

Journal
Journal of Special Education Technology
Published
2026-11-21
DOI
https://doi.org/10.1177/01626434261509965
Primary Topic
Behavioral and Psychological Studies
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Using Matrix Training to Promote Oral WH-Syntax Production in Chinese-Speaking Autistic Children: A Human-AI Collaborative Instructional Design

Liming Zhou, Xiaoyi Hu, Xueting Qi, Jiamei Zhao et al.
Journal of Special Education Technology
Behavioral and Psychological Studies
article

Using Matrix Training to Promote Oral WH-Syntax Production in Chinese-Speaking Autistic Children: A Human-AI Collaborative Instructional Design

Liming Zhou, Xiaoyi Hu, Xueting Qi, Jiamei Zhao, Xiaoyu Liu, Xiaoya Wu, Yuanyuan Mei, Junyan Chen, Lin Wang, Yifei Meng
article en

Abstract

Matrix training is an evidence-based approach for fostering generative language in autistic children, yet its application to high-dimensional syntactic structures remains limited by the logistical demands of stimulus preparation. This study evaluated a structured instructional protocol supported by a human-AI collaborative design process to improve the oral production of five-element WH-syntax (Who, When, Where, How, and Doing What) in 10 Chinese-speaking autistic children. Utilizing a multiple-probe design across participants, generative AI was employed under expert practitioner supervision to assist in developing a culturally adaptive 126-item instructional matrix from a theoretical universe of 162 permutations. Results indicated that all 10 participants achieved mastery criteria within an average of 8.1 instructional sessions (8 trials per session). Between-case standardized mean difference estimates indicated a substantial intervention effect size (BC-SMD = 30.33, 95% CI [27.53, 33.13]), and participants demonstrated skill transfer across novel stimulus combinations and follow-up maintenance probes. These preliminary findings suggest that human-guided AI support can reduce preparation barriers for educators, providing a feasible framework for delivering complex syntactic instruction in special education settings.

Journal of Special Education Technology
Tianjin Normal University (CN), Qingdao Binhai University (CN), Beijing Normal University (CN), Center for Autism and Related Disorders (US)
Behavioral and Psychological Studies
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
Using Matrix Training to Promote Oral WH-Syntax Production in Chinese-Speaking Autistic Children: A Human-AI Collaborative Instructional Design — Liming Zhou, Xiaoyi Hu, et al. · Journal of Special Education Technology (2026) | TGRS Research Map | TGRS