Gaze-based assistance produced a significantly higher follow-up fixation rate on the spoken secondary AOI than the baseline¶

Claim · All claims
Evidence · 1 study (2 entries) · causal r1 · q3
Currency · newest study 2026 · not yet checked against its sources · not reviewed by a person

Subclaims¶

q3 i? Children fixated the secondary AOI during a significantly higher proportion of gaze-based assistance instances (M = 54.06%) than baseline instances (M = 35.48%), p < .05. → Zekun Wu 2026 q3 i? Relevance distance between primary and secondary AOIs was significantly lower in the gaze-based condition (M = 0.43) than in the baseline condition (M = 0.52), p < .001. → Zekun Wu 2026 (2)

Evidence¶

Zekun Wu 2026¶

Zekun Wu, Man Su, Huiyong Li, Tomohiro Nagashima, and Anna Maria Feit. (2026). Gaze-Informed Proactive AI Assistance for Children Exploring Picture Books. https://arxiv.org/abs/2607.00445 doi:10.48550/arxiv.2607.00445

q3 · i? · causal · r1

Within-subject gaze analysis; the secondary AOI was introduced only through speech without visual highlighting, so attention shifts reflect verbal suggestion. The gaze condition reached "M = 54.06%, SD = 20.92%" vs. 35.48% in baseline; no effect size printed.

"the gaze-based condition yields a significantly higher follow-up fixation rate on the secondary AOI (M = 54.06%, SD = 20.92%) than the baseline condition (M = 35.48%, SD = 28.34%), with a statistically significant difference (𝑝<. 05)."

Zekun Wu 2026 (2)¶

Zekun Wu, Man Su, Huiyong Li, Tomohiro Nagashima, and Anna Maria Feit. (2026). Gaze-Informed Proactive AI Assistance for Children Exploring Picture Books. https://arxiv.org/abs/2607.00445

q3 · i? · causal · r1

Direct comparison of the weighted relevance distance (Equation 2 combining semantic, spatial, and temporal distances) between selected AOI pairs in the two conditions of the within-subject study. "M = 0.43, SD = 0.10" vs. 0.52; no effect size printed.

"In the gaze-based condition, relevance distance between the primary AOI and the secondary one (M = 0.43, SD = 0.10) is significantly lower than the baseline condition (M = 0.52, SD = 0.13, p < .001)."

Discussion¶

Related Claims¶

• Most children and parents preferred gaze-based assistance over the LLM baseline — related
• Follow-up fixation rate on the primary AOI did not differ significantly between gaze-based and baseline assistance — related
• Attention allocated to the secondary AOI remained limited and did not differ significantly between conditions in duration or time to first fixation — related
• Gaze-based assistance supported a smoother attention transition between narrated regions, while baseline assistance elicited more abrupt reorientation — related
• Gaze-based assistance led children to fixate the narrated primary AOI significantly longer than LLM-baseline assistance — related
• Proactive feedback produces significant post-intervention increases in Joint Visual Attention of dyads — related
• Large arrays exceed young children's attentional resources, preventing optimal allocation to relevant items — related
• Teachers and students use gaze to express agency and communion during classroom problem-solving — related