ArXiv proposal tests voice-based AI interviews for university course feedback
Discovery source: Research authors via arXiv · Source date:
A research proposal on arXiv from Thilo Tamme and coauthors describes a higher-education field study of voice-based conversational AI interviews for course feedback. Submitted on October 18, 2026, the paper argues that spoken AI interviews may address common problems in end-of-semester surveys, including low response rates, superficial answers, and limited actionability. The planned study will be run in MIT Sloan’s Advanced Leadership Communication course with about 60 students, using a convergent mixed-methods design and a four-dimensional actionability coding framework. The authors frame the work as a proposal and feasibility study, not a reported learning-outcomes result, and say a prior technical pilot at TUM showed telephone-based AI interviews were feasible.
Check the sources
This is a NextGen-AI briefing, not a reproduction of the discovery source. A newsletter may cover several developments; consult the evidence below for this briefing’s specific subject. The source date refers to the discovery entry, not necessarily the announcement date.