TY - GEN
T1 - Modeling One-on-one Online Tutoring Discourse using an Accountable Talk Framework
AU - Balyan, Renu
AU - Arner, Tracy
AU - Taylor, Karen
AU - Shin, Jinnie
AU - Banawan, Michelle
AU - Leite, Walter L.
AU - McNamara, Danielle S.
N1 - Publisher Copyright:
© 2022 Copyright is held by the author(s).
PY - 2022
Y1 - 2022
N2 - The National Council of Teachers of Mathematics (NCTM) has been emphasizing the importance of teachers’ pedagogical communication as part of mathematical teaching and learning for decades. Specifically, NCTM has provided guidance on how teachers can foster mathematical communication that positively impacts student learning. A teacher may have different academic goals towards what needs to be achieved in a classroom, which require a variety of discourse-based tools that allow students to engage fully in mathematical thinking and reasoning. Accountable or academically productive talk is one such approach for classroom discourse that may ensure that the discussions are coherent, purposeful and productive. This paper discusses the use of a transformer model for classifying classroom talk moves based on the accountable talk framework. We investigate the extent to which the classroom Accountable Talk framework can be successfully applied to one-on-one online mathematics tutoring environments. We further propose a framework adapted from Accountable Talk, but more specifically aligned to one-on-one online tutoring. The model performance for the proposed framework is evaluated and compared with a small sample of expert coding. The results obtained from the proposed framework for one-on-one tutoring are promising and improve classification performance of the talk moves for our dataset.
AB - The National Council of Teachers of Mathematics (NCTM) has been emphasizing the importance of teachers’ pedagogical communication as part of mathematical teaching and learning for decades. Specifically, NCTM has provided guidance on how teachers can foster mathematical communication that positively impacts student learning. A teacher may have different academic goals towards what needs to be achieved in a classroom, which require a variety of discourse-based tools that allow students to engage fully in mathematical thinking and reasoning. Accountable or academically productive talk is one such approach for classroom discourse that may ensure that the discussions are coherent, purposeful and productive. This paper discusses the use of a transformer model for classifying classroom talk moves based on the accountable talk framework. We investigate the extent to which the classroom Accountable Talk framework can be successfully applied to one-on-one online mathematics tutoring environments. We further propose a framework adapted from Accountable Talk, but more specifically aligned to one-on-one online tutoring. The model performance for the proposed framework is evaluated and compared with a small sample of expert coding. The results obtained from the proposed framework for one-on-one tutoring are promising and improve classification performance of the talk moves for our dataset.
KW - accountable talk framework
KW - classroom discourse
KW - one-on-one online tutoring
KW - transfer learning
UR - http://www.scopus.com/inward/record.url?scp=85174848760&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85174848760&partnerID=8YFLogxK
U2 - 10.5281/zenodo.6852936
DO - 10.5281/zenodo.6852936
M3 - Conference contribution
AN - SCOPUS:85174848760
T3 - Proceedings of the 15th International Conference on Educational Data Mining, EDM 2022
BT - Proceedings of the 15th International Conference on Educational Data Mining, EDM 2022
PB - International Educational Data Mining Society
T2 - 15th International Conference on Educational Data Mining, EDM 2022
Y2 - 24 July 2022 through 27 July 2022
ER -