TalkMoves
An important benchmark dataset in educational discourse research, derived from transcriptions of authentic US K-12 mathematics classroom recordings. It is used to annotate discourse strategies that promote student thinking in teacher-led classroom discussions, as proposed by education researchers Michaels and O'Connor.
Timeline (last 90 days)
The EduBehaviors framework is validated on the TalkMoves dataset with the task of predicting teacher Talk Moves labels.
Under the optimal configuration, the EduBehaviors framework achieves a macro F1 score of 0.673 and a Cohen's kappa of 0.688.
The TalkMoves dataset is derived from transcriptions of real recordings of U.S. K-12 mathematics classrooms, and the concept of Talk Moves was proposed by education researchers Michaels and O'Connor.
On the TalkMoves task, a Cohen's kappa above 0.6 is considered an acceptable baseline.
All Facts (4)
The EduBehaviors framework is validated on the TalkMoves dataset with the task of predicting teacher Talk Moves labels.
50%UnverifiedUnder the optimal configuration, the EduBehaviors framework achieves a macro F1 score of 0.673 and a Cohen's kappa of 0.688.
50%UnverifiedThe TalkMoves dataset is derived from transcriptions of real recordings of U.S. K-12 mathematics classrooms, and the concept of Talk Moves was proposed by education researchers Michaels and O'Connor.
50%UnverifiedOn the TalkMoves task, a Cohen's kappa above 0.6 is considered an acceptable baseline.
50%