TalkMoves shows higher inter-rater reliability (k=0.74) than a hybrid codebook (k=0.64) but lower coverage and usability when applied to one-on-one tutoring across modalities, with both struggling on nonverbal elements.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.HC 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Does the TalkMoves Codebook Generalize to One-on-One Tutoring and Multimodal Interaction?
TalkMoves shows higher inter-rater reliability (k=0.74) than a hybrid codebook (k=0.64) but lower coverage and usability when applied to one-on-one tutoring across modalities, with both struggling on nonverbal elements.