Atypical attention in Autism Spectrum Disorder (ASD) presents challenges to children's learning and daily functioning. Traditional assessments like the Attention Network Test (ANT) often fail to engage autistic children due to their abstract and repetitive nature, leading to low task completion and limited data. To address this gap, we developed ATTENPlay on a tablet, a game-based assessment from a systematic, expert-led co-design process that translates ANT tasks into a child-friendly narrative with single-tap interactions. We conducted a study with 52 children (28 autistic, 24 neurotypical) to evaluate the proposed ATTENPlay. Our findings indicate ATTENPlay significantly improves usability and user experience compared to the traditional paradigm. The assessment also captured interpretable cognitive data, revealing significant group differences in both the orienting and executive control networks. This work contributes a game-based tool that supports more accessible attention network testing for autistic children and demonstrates an inclusive design process for creating cognitive assessments.
Existing children’s self-reporting tools like surveys and diaries often feel restrictive, leading to disengagement and low-quality responses. LLM-powered chatbots can adapt with simplified wording or empathetic tone, but such adaptations remain insufficient: responses may be adult-centered, complex, or formulaic, undermining engagement and response quality. We explore rhyme as a child-centered conversational style. In a co-design workshop with 35 children, participants envisioned dialogue that was short, playful, and soothing. Building on these insights, we designed a voice-based sleep diary in rhyming style and conducted a within-subjects study (rhyming vs. prose) with 42 children. Rhyming prompts improved response quality across question types, while maintaining high engagement even among children who preferred prose. We contribute empirical evidence and design insights showing how rhyme can exemplify broader child-centered strategies beyond capability adaptation. Although limited to short-term lab sessions, this work provides a first step toward conversational style as a design lever for children’s self-reporting.
Role-play is widely used to empower autistic children to explore social interaction and dynamics on their own terms, navigating neurotypical social conventions to shape social expressions in ways that align with their own traits and needs, fostering a stronger sense of agency. However, existing approaches typically rely on fixed content, requiring educators to design materials, which creates a significant burden on manual preparation. According to insights from a formative study, we developed GenRole, a generative AI system that enables educators to design personalized role play class activities. GenRole supports a progression from simple to complex interactions and allows for personalization of characters, settings, and dialogues that meet the needs of autistic learners. We conducted a pilot study with 16 educators, followed by a two-week evaluation study with 11 autistic children and their teachers. Results show that GenRole enhances the efficiency and flexibility of role play design while improving instructional support, offering design insights for creating personalized components that help educators deliver more engaging and individualized social interaction learning for autistic children.
Digital sleep diaries are widely used to monitor children’s sleep, yet response quality is often low because children may not know how, or be motivated, to give detailed answers. We investigate how “live,” continuous feedback in voice-based sleep diaries can support higher-quality responses. In a co-design workshop, we explored children's preferences for different forms of feedback. We designed and compared experimentally symbolic, numeric, and no-feedback conditions, showing that both feedback types improved response quality across questions. Finally, an eight-day field study revealed that feedback resulted in higher and more consistent quality in self-report over time. Across these three studies, children valued playful and clear feedback, with preferences shifting depending on their cognitive needs. Our findings demonstrate that effective feedback must balance affective engagement with cognitive clarity and adapt to different contexts. We contribute empirically supported design insights to enhance children's adherence and response quality in voice-based self-report surveys.
Recent advances in generative AI have introduced a new programming paradigm—vibe coding, a natural language–driven mode of AI collaboration. While promising for adults, little is known about how children engage with this approach, especially in block-based environments. To explore this gap, we conducted workshops with children of varying Scratch experience (n=41) and interviewed five Scratch teachers. Our study investigates how vibe coding impacts children’s programming learning and practice, and what challenges arise. Findings show that vibe coding has both positive and negative impacts across three key contexts of children’s programming experience: acquisition, application, and creation. Across the stages of vibe coding—goal articulation, information interpretation, and outcome evaluation—children encounter distinct challenges. By examining the mismatches between core assumptions of vibe coding and children’s needs, and analyzing its applicability across different contexts, we offer child-centered design implications for future vibe coding systems and GenAI tools.
As K–12 computer science expands in the United States, students encounter a growing array of programming tools. Many introductory experiences use block-based environments, where programs are assembled by snapping together visual blocks instead of typing code. While these tools can support learning, high school students often perceive them negatively, even when they support the same underlying logic as text-based coding. Using a constructivist grounded theory approach, we interviewed 17 high school students to trace how early experiences, tool design, peer discourse, and cultural framings shape these views. We find that students develop informal folk theories: that computer science is about accumulating languages, that block-based programming is for young children, and that limitations in programming activities stem from the block modality itself—beliefs that can shift when students encounter counterexamples. Our findings call for more deliberate design and sequencing of tools that are attentive to the meanings students construct as they progress, and that promote more expansive notions of programming beyond modality.
Autistic children exhibit heterogeneous oral language impairments, necessitating educators to implement personalized teaching content. However, preparing personalized materials remains time-intensive and difficult to maintain coherence, while generative AI's recent advances in creating customized content show potential to support this process. We first conducted video analysis from educators' one-on-one classes with autistic students and conducted interviews with therapists to understand their challenges in current teaching practices. Then, we developed a generative AI-empowered prototype, LingoLift, which supports educators to create interest-based, ability-adapted, and coherent teaching materials according to children's profiles. Finally, we conducted a three-week deployment study with 10 educator-student dyads completing 30 lessons with LingoLift in a specialized education school. Results showed that LingoLift significantly improved lesson preparation efficiency, reduced educators' workload, and enabled children to achieve positive learning outcomes. We observed educators' adaptive extensions and innovations, revealing insights into design considerations and future opportunities for AI-assisted inclusive education.