SVM-based mind wandering detector achieved 69% precision and 67% recall generalizing to new learners¶

Claim · All claims
Evidence · 1 study · theoretical r3 · q2
Currency · newest study 2016 · not yet checked against its sources · not reviewed by a person

Subclaims¶

q2 i? A support vector machine discriminated mind wandering from eye gaze with a precision of 69% and a recall of 67%, designed to generalize to new learners. → D’Mello 2016

Evidence¶

D’Mello 2016¶

D’Mello, S. K. (2016). Giving Eyesight to the Blind: Towards Attention-Aware AIED. International Journal of Artificial Intelligence in Education. https://doi.org/10.1007/s40593-016-0104-1

q2 · i? · theoretical · r3

Data from 98 learners reading a 57-page scientific text on surface tension, tracked with a Tobii TX 300 eye tracker, trained a support vector machine to discriminate mind wandering (pages with a self-report — 32%) from normal reading. The article reports "The model had a precision of 69 % and a recall of 67 %".

"The model had a precision of 69 % and a recall of 67 %, which we deemed to be sufficiently accurate for our purposes"

Discussion¶

Related Claims¶

• D'Mello proposes attention tracking and management as a new AIED research direction — a broader claim this one bears on
• Lab-trained mind wandering detectors generalize to in-the-wild lecture viewing across task, setting, and cultural group, with BiLSTM on latent features reaching F1 = 0.352 — related