Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
September 23, 2025PLoS ONEOpen Access

Comparative analysis of AI and expert evaluations in engineering design pedagogy

View Full Paper
Ask AI
Bookmark
Share

Authors

TCTuğra Karademir CoşkunEAEsra Bozkurt Altan

Discussion

Loading...

Member takes

Overview

Mixed-methods study examines AI evaluations versus expert assessments in lesson plan development, suggesting strong reliability in structured prompts.

Key Points

  • High consistency in evaluations from AI using structured prompts compared to experts, indicating promising reliability.
  • Evaluations showed an Intraclass Correlation Coefficient of 0.708 for structured prompts, indicating robust agreement between AI and expert feedback.
  • Qualitative analysis revealed that AI feedback tends to be more positive and holistic compared to the critical nature of expert evaluations.
  • Unstructured AI prompt evaluations produced inconsistent results, requiring further refinement to enhance evaluation reliability.

Cite This Study

Coşkun et al. (2025) studied this question.

synapsesocial.com/papers/68d473a631b076d99fa6bddfhttps://doi.org/10.1371/journal.pone.0332715
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Generative AI tools as educators’ assistants: Designing and implementing inquiry-based lesson plans2024 · 115 citations
  2. 2Assessment of Students Use of Generative Artificial Intelligence: Prompting Strategies and Prompt Engineering in Chemistry Education2024 · 115 citations
  3. 3Beyond the basics: a detailed conceptual framework of integrated STEM2021 · 207 citations
  4. 4Engineering Design and Manufacturing Education through Research Experience for High School Teachers2018 · 13 citations
  5. 5Enhancing engineering education in the elementary school2019 · 32 citations