#formative feedback

formative feedback

3 논문

A lecturer and two design students compare a service storyboard with annotated feedback sheets while a student records revision ideas.

학회 논문2025

Students preferred AI design feedback in a small study, while improvements in design quality were not established

Tanja Katharina Schmitt-Fumian, Selina Tauscher, Katja Thoring

Proceedings of the Design Society (ICED25)

An ICED 25 study asked 25 students to compare GPT-4 feedback with comments from human educators on a design-ideation task. Students generally rated the AI comments more positively for support, clarity and organization. Feedback order was randomized, and interviews explored the reasons for preferences. The study measured reception of textual comments, not independently rated improvements in designs or later creative ability, and substantial prompt-development work preceded the comparison.

design educationformative feedbackhuman-AI collaboration

500단어 요약 읽기 →

Two students and an instructor inspect polarizer components while comparing an annotated light-path diagram in an optics teaching laboratory.

저널 논문2025

저널 논문 172

AI feedback improved answers during an augmented-reality physics lab, while independent transfer was not assessed

Atakan Coban, David Dzsotjan, Stefan Küchemann, Jürgen Durst, Jochen Kuhn, Christoph Hoyer

EPJ Quantum Technology

A physics laboratory study compared feedback and no-feedback questions within an augmented-reality quantum-cryptography activity involving 21 student groups. GPT-4 feedback helped groups improve their immediate explanations, while gaze records suggested changes in attention to relevant representations and equipment. The measured outcome was answer improvement during supported discussion. A small voluntary sample, exploratory gaze analyses and no independent delayed test limit broader claims about learning and the value of the combined technology.

physics educationaugmented realityformative feedback

500단어 요약 읽기 →

Two preservice teachers revise a five-part whiteboard mind map while a teaching assistant checks an annotated feedback sheet beside them.

저널 논문2025

저널 논문 122

Multilevel AI-assisted feedback supported collaborative regulation, with human review built into delivery

Guoqing Lu, Shen Ba, Lan Yang

Education and Information Technologies

A study of 114 preservice teachers compared four designs for AI-assisted formative feedback during collaborative learning. Feedback addressing task, process, and self-regulation showed advantages on several group outcomes over task-only comments, while adding detail was not uniformly better. A teaching assistant reviewed and delivered the feedback, so the findings concern a supervised instructional workflow rather than students using an autonomous chatbot or AI outperforming teacher feedback.

collaborative learningformative feedbackteacher education

500단어 요약 읽기 →