Frontiers in psychology · 2026
Can AI-driven games enhance social skills for autistic children? - A three-level meta-analysis.
СтатьяОбзорНазвание и аннотация: Перевод в очереди
Обработка статьи · этапы, ошибки и управление
Загрузка состояния…
Ошибки и ограничения
История · было → стало
Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.
Lu Hang, Zhao Jiayao, Zhang Yi, Cheng Wei
Аннотация
BACKGROUND: Gamified interventions for autistic children are becoming increasingly diverse, enhancing their presence, immersion, and sense of accomplishment to improve various social skill indicators. Existing systematic reviews have primarily evaluated intervention effectiveness from the perspectives of game design and intervention objectives. However, these findings are inconsistent and fail to inspect specific improvements in social skills among autistic children.
METHODS: To address this gap, this study adopts a three-level meta-analysis approach from the perspective of AI-driven games, examining 14 relevant publications across 9 databases up to March 2026, totaling 37 effect sizes. At the same time, to understand the causes of heterogeneity, the study systematically examined the impact of seven moderating factors on intervention outcomes for autistic children: study design, sample size, intervention goals, measurement tools, intervention frequency, intervention duration, and artificial intelligence technology.
RESULTS: The overall effect size of AI-driven gamified interventions on the social skills of autistic children was Hedges'g = 0.511 (95% CI [0.346, 0.677], p < 0.001), indicating a moderate positive effect. Specifically, regarding the improvement of social skills in autistic children through AI-driven games, the intervention targeting emotional expression and recognition achieved a moderate and significant effect size (Hedges'g = 0.536, p < 0.01), while the intervention targeting the dual development of attention and social skills reached a large effect size (Hedges'g = 0.963). The remaining skills, such as attention, communication skills, and daily living skills all reached a moderate effect size level (Hedges'g = 0.644, 0.650, 0.618). The moderating effect of AI technology was significant (Q(5) = 7.481, p < 0.001) and was primarily driven by differences in specific technology types rather than by complex hierarchical structures. Additionally, the study systematically identified 14 gamification elements and distilled the core components, including: feedback mechanisms, reward systems, and level design.
CONCLUSION: This study provides preliminary evidence that current AI-based gamified interventions can effectively improve the social skills of autistic children. However, it should be noted that this study has certain limitations. Future research should include more high-quality RCTs to explore the validity of intervention effects and systematically examine the optimal configuration of different combinations of AI technologies and gamification elements.
METHODS: To address this gap, this study adopts a three-level meta-analysis approach from the perspective of AI-driven games, examining 14 relevant publications across 9 databases up to March 2026, totaling 37 effect sizes. At the same time, to understand the causes of heterogeneity, the study systematically examined the impact of seven moderating factors on intervention outcomes for autistic children: study design, sample size, intervention goals, measurement tools, intervention frequency, intervention duration, and artificial intelligence technology.
RESULTS: The overall effect size of AI-driven gamified interventions on the social skills of autistic children was Hedges'g = 0.511 (95% CI [0.346, 0.677], p < 0.001), indicating a moderate positive effect. Specifically, regarding the improvement of social skills in autistic children through AI-driven games, the intervention targeting emotional expression and recognition achieved a moderate and significant effect size (Hedges'g = 0.536, p < 0.01), while the intervention targeting the dual development of attention and social skills reached a large effect size (Hedges'g = 0.963). The remaining skills, such as attention, communication skills, and daily living skills all reached a moderate effect size level (Hedges'g = 0.644, 0.650, 0.618). The moderating effect of AI technology was significant (Q(5) = 7.481, p < 0.001) and was primarily driven by differences in specific technology types rather than by complex hierarchical structures. Additionally, the study systematically identified 14 gamification elements and distilled the core components, including: feedback mechanisms, reward systems, and level design.
CONCLUSION: This study provides preliminary evidence that current AI-based gamified interventions can effectively improve the social skills of autistic children. However, it should be noted that this study has certain limitations. Future research should include more high-quality RCTs to explore the validity of intervention effects and systematically examine the optimal configuration of different combinations of AI technologies and gamification elements.