M-Powering Teachers: Natural Language Processing Powered Feedback Improves 1:1 Instruction and Student Outcomes


Conference paper


Dorottya Demszky, Jing Liu
L@S '23: Proceedings of the Tenth ACM Conference on Learning @ Scale, 2023 , pp. 59-69


View PDF
Cite

Cite

APA   Click to copy
Demszky, D., & Liu, J. (2023). M-Powering Teachers: Natural Language Processing Powered Feedback Improves 1:1 Instruction and Student Outcomes (pp. 59–69). L@S '23: Proceedings of the Tenth ACM Conference on Learning @ Scale. https://doi.org/10.1145/3573051.3593379


Chicago/Turabian   Click to copy
Demszky, Dorottya, and Jing Liu. “M-Powering Teachers: Natural Language Processing Powered Feedback Improves 1:1 Instruction and Student Outcomes.” In , 59–69. L@S '23: Proceedings of the Tenth ACM Conference on Learning @ Scale, 2023.


MLA   Click to copy
Demszky, Dorottya, and Jing Liu. M-Powering Teachers: Natural Language Processing Powered Feedback Improves 1:1 Instruction and Student Outcomes. L@S '23: Proceedings of the Tenth ACM Conference on Learning @ Scale, 2023, pp. 59–69, doi:10.1145/3573051.3593379.


BibTeX   Click to copy

@inproceedings{dorottya2023a,
  title = {M-Powering Teachers: Natural Language Processing Powered Feedback Improves 1:1 Instruction and Student Outcomes},
  year = {2023},
  month = dec,
  pages = {59-69},
  publisher = {L@S '23: Proceedings of the Tenth ACM Conference on Learning @ Scale},
  doi = {10.1145/3573051.3593379},
  author = {Demszky, Dorottya and Liu, Jing},
  month_numeric = {12}
}

Although learners are being connected 1:1 with instructors at an increasing scale, most of these instructors do not receive effective, consistent feedback to help them improve. We deployed M-Powering Teachers, an automated tool based on natural language processing to give instructors feedback on dialogic instructional practices ---including their uptake of student contributions, talk time and questioning practices --- in a 1:1 online learning context. We conducted a randomized controlled trial on Polygence, a research mentorship platform for high schoolers (n=414 mentors) to evaluate the effectiveness of the feedback tool. We find that the intervention improved mentors' uptake of student contributions by 10%, reduced their talk time by 5% and improved student's experience with the program as well as their relative optimism about their academic future. These results corroborate existing evidence that scalable and low-cost automated feedback can improve instruction and learning in online educational contexts.

Share



Follow this website


You need to create an Owlstown account to follow this website.


Sign up

Already an Owlstown member?

Log in