One point per second, weighted by observed duration. Gaps mean no assessment. Partial seconds use only their observed time.
Start the camera to begin a session.
Higher requires a stronger smile. Changes affect new observations; reset for a fresh comparison.
Window: 0.0 s. Each row totals 100% of this period, including time without an assessment.
| State | Yes | No | No assessment |
|---|---|---|---|
| Looking at camera | — | — | — |
| Speaking · lip movement | — | — | — |
| Smiling | — | — | — |
| Gaze | Speaking | Not speaking |
|---|---|---|
| At camera | — | — |
| Away | — | — |
Joint state unknown: —
| Speech with gaze at camera | — |
| Speaking while looking | — |
| Smile in observed time | — |
| Joint observation coverage | — |
All four indicator percentages always cover the entire session. Person in frame counts any detected face; other states require one usable participant. Missing assessments stay separate in this table. Lip movement and smile are visual estimates.