TalkBack

CU Boulder’s TalkBack cyberlearning tool uses natural language processing to provide teachers with automated feedback about their use of academically productive discourse in class

TalkBalk is a teaching tool under development by the Institute of Cognitive Sciences at the University of Colorado (CU) Boulder that processes the transcripts of teaching sessions in order to provide feedback to teachers looking to promote academically productive discourse in class.

“Talk moves” are one example of academically productive discourse – phrases and questions that foster an environment of active listening, contextualisation of complex ideas, collaborative learning, and the respectful construction and delivery of explanations, arguments and counter-arguments.

Goal	Talk move	Example
1. Accountability to the learning community	Keeping everyone together Getting students to relate to another’s ideas	“What did she just say?” “Who agrees and who disagrees?”
2. Ensuring purposeful coherent and productive group discussion	Restating Revoicing	“Let me say back what I heard.” “Let me say back what I heard and add on.”
3. Accountability to rigorous thinking	Pressing for accuracy Pressing for reasoning	“Can you tell us the steps you used to find the answer?” “How are these ideas connected?”

Teachers can, through self-assessment, improve their use of talk moves in the classroom. Wayne et al. (2018) show that providing educators with long-term information about their instructional practices for two years improved students’ math achievement after the first year by about four weeks of learning. Tracking the use of different talk moves in class is essential feedback for any teacher wishing to monitor their students’ progress. However, providing teachers with feedback about their instruction, or the conversational progress underway by the children in their classes, requires lengthy, detailed and expensive observation by experts, who would need to transcribe every classroom session and categorize, by hand, individual exchanges into individual talk moves (Suresh et al. 2018).

Academically productive discourse especially helps girls, and other demographics frequently in the minority in STEM fields, maintain an interest in mathematics by providing a social context that has been shown to improve self-assessment of mathematical abilities. This can lead to a more diverse cohort to choose STEM career paths resulting in a positive societal effect, injecting much-needed diversity into increasingly homogeneous STEM fields.

For more information on TalkBack, please visit the TalkBack homepage at ICS, CU Boulder

References

Suresh, A., Sumner, T., Jacobs J. et al., (2019). “Automating analysis and feedback to improve mathematics teachers’ classroom discourse”, the ninth symposium on Educational Advances in Artificial Intelligence (EAAI).

Wayne, A., Garet, M., Wellington, A. and Chiang, H. (2018). Promoting educator effectiveness: The effects of two key strategies. NCEE 2018-4009. National Center for Education Evaluation and Regional Assistance.