19 lines
3.2 KiB
Markdown
19 lines
3.2 KiB
Markdown
<!-- Source: Kon Master Brief — Appendix A2: AI Body Doubling -->
|
||
|
||
## A2. AI Body Doubling — Controlled Studies
|
||
|
||
**Core finding:** AI-driven body doubles are statistically indistinguishable from human body doubles for task efficiency and sustained attention (p = 1.000), whilst eliminating the social anxiety that many neurodivergent users experience with human co-presence.
|
||
|
||
**Primary evidence:**
|
||
- **Ara et al. 2025** (arXiv:2509.12153): 12 adults with ADHD in a VR bricklaying task across three conditions — alone (C1), human body double (C2), AI body double (C3). Repeated-measures ANOVA: **F(2,22) = 6.51, p = 0.006**. Both human and AI body doubles improved task efficiency by **27–30%** over working alone (8.49 vs 10.82 and 11.06 bricks per minute). **No significant difference between human and AI (p = 1.000)**. Some participants preferred AI specifically because it reduced social anxiety and performance pressure.
|
||
- **Eagle, Baltaxe-Admony & Ringland 2024** (*ACM TACCESS*): Survey of **193 neurodivergent participants** establishing that body doubling operates on a continuum of space/time and mutuality. Non-human presence — animated characters, "Study With Me" videos, even ambient audio — can function as a body double, grounded in parasocial relationship theory.
|
||
- **O'Connell et al. 2024** (*ACM/IEEE HRI '24*): Socially assistive robot (Blossom) as body double for 11 ADHD university students over three weeks. **91% voluntarily continued using the robot**. System Usability Scale score: **83.86** (above "good" threshold). Non-judgmental passive presence was the most-valued attribute.
|
||
- **Lalwani, Saleh & Salam 2025** (*HRI '25*): Robot companions providing active micro-scaffolding (goal reminders, encouragement) outperformed mere passive presence. 80% of 15 ADHD participants expressed interest in continued use — suggesting the ideal design combines ambient presence with context-aware nudges.
|
||
- **Cuber et al. 2024** (*ACM CHI '24*): VR study environment for 27 ADHD university students across up to 12 sessions. **Significant increases in concentration, motivation, and effort** during VR sessions vs. baseline.
|
||
- **Schuenke, Dickenson & Moore 2025** (*ACM ASSETS '25*): First study to use EEG for objective neurophysiological markers of attentional state during body doubling — moving beyond self-report.
|
||
- **Papadopoulos 2025** (*SAGE*): AI chatbot use among autistic individuals provides **"qualitatively different and more profound"** support through judgment-free, on-demand interaction.
|
||
|
||
**Theoretical basis:** Barkley's (1997) model of ADHD as a disorder of behavioural inhibition prescribes externalisation of executive functions — moving regulatory demands from impaired internal systems into the environment. Body doubling is precisely this: an external source of temporal anchoring, accountability, and arousal regulation.
|
||
|
||
**Implication for Kon:** The low-fi "Focus Room" (section 4) is strongly validated. Combine ambient AI presence with context-aware nudges for maximum effect. The AI option specifically reduces barriers for autistic users whilst maintaining comparable efficacy. Design should include: simulated progress indicators, rhythmic work pacing cues, and subtle ambient motion for divided attention support.
|