PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
February 27, 2026Academic Medicine0 citationsOpen Access

Bridging the Gap: Use of Automated Text Analysis to Support Interpretation of Narrative Feedback

View Full Paper
JLJoyce M. W. Moonen-van LoonMGMarjan GovaertsMLMarion van Lierop

Key Points

  • This report aims to enhance the interpretation of narrative feedback through an automated tool tailored for educational outcomes.
  • Developed and piloted an automated text analysis tool in a master's program in medicine.
  • Conducted collaborative design sessions with stakeholders to align tool functionality with educational needs.
  • Utilized topic modeling and sentiment analysis to visualize feedback data in relation to competencies.
  • The tool was successfully piloted with 33 students and 20 mentors.
  • Participants reported improved reflection on competency development and informed mentorship.
  • Key benefits included clear visual representation of feedback aligned with intended learning outcomes.

Abstract

Abstract Problem Interpretation of large volumes of narrative feedback, collected in a programmatic assessment setting, poses significant challenges for students, mentors, and assessors. This report introduces an innovative tool designed to provide personalized, real-time interpretations of narrative feedback aligned with predefined learning outcomes. Approach Through collaborative design sessions with key stakeholders, the authors developed and piloted the tool within the master’s in medicine program at Maastricht University from February 2022 to May 2024. The tool’s algorithm combines topic modeling and sentiment analysis to provide visual representations of feedback data mapped onto predefined competencies and professional activities. Outcomes The innovation was piloted in the master’s program in medicine at Maastricht University, the Netherlands, between December 2023 and April 2024. A total of 33 students, approximately 2 years into the 3-year program, and their 20 mentors participated in the pilot. Both mentors and students acknowledged the tool’s potential to enhance effective use of narrative feedback data. Students predominantly used the tool to reflect on and self-assess their competency development and set new learning goals, whereas mentors leveraged it to guide and monitor students’ learning and provide informed advice to the clinical competency committee on students’ competence development. Key benefits included the visualization of feedback data aligned with intended learning outcomes and comprehensive identification of strengths, areas for improvement, and learning gaps. Next Steps Informed by pilot insights, the tool will be refined and tested in an expanded pilot. The tool’s adaptable structure allows integration into diverse educational frameworks, incorporation of domain-specific terms, and deployment within e-portfolios or as a standalone tool. This scalable innovation offers a robust solution for enhancing the interpretation and use of narrative feedback and can be applied globally across a wide range of educational programs that use overarching (eg, competency-based) assessment frameworks.

Ask AI
Helpful
Bookmark
Share
View Full Paper

Cite This Study

Loon et al. (2026) studied this question.

synapsesocial.com/papers/69a13571ed1d949a99abf42ehttps://doi.org/10.1093/acamed/wvag049
Ask AI
Helpful
Bookmark
Share
View Full Paper