Open-ended learner feedback revealed four themes: trust in AI scaffolding, feedback clarity, engagement, and task authenticity¶

Claim · All claims
Evidence · 1 study · design r2 · q2
Currency · newest study 2026 · not yet checked against its sources · not reviewed by a person

Subclaims¶

q2 i? Open-ended survey responses yielded four recurring themes, with participants valuing guided hint-based support and realistic scenarios while requesting shorter, more structured feedback. → Hornung 2026

Evidence¶

Hornung 2026¶

Hornung, I., Marasinghe Arachchige, D., Kumarage, T., Agrawal, G., Deng, Y., Chen, Y.-C., & Liu, H. (2026). CyberAGENTS: Structured Autonomy for Agentic Gamified Learning in Cybersecurity. Preprint. https://arxiv.org/abs/2608.07965 doi:10.48550/arxiv.2608.07965

q2 · i? · design · r2

Qualitative thematic analysis of open-ended post-study survey responses from the 24-participant classroom deployment. Participants "consistently valued the realism of the scenarios and the BuddyAgent's guided support" and requested shorter, more structured responses and more immersive interaction formats.

"Open-ended responses revealed four recurring themes: trust in AI scaffolding, clarity of feedback, engagement and interaction design, and authenticity of tasks"

Discussion¶

Related Claims¶

• Undergraduate learners rated CyberAGENTS positively, with scenario authenticity highest and challenge difficulty alignment lowest — related
• Topic modeling of open-ended responses revealed five themes centered on ChatGPT's simplicity, speed, and role as a support tool — related
• 90% of open-ended survey responses about the ChatGPT activity were neutral in sentiment, with 2% positive and 8% negative — related
• Qualitative themes: efficiency and peer influence drive AI use, while confidence and rule ambiguity shape students' perceptions of dependence — related
• Thematic analysis of open responses surfaced four themes: immediacy as core value, calibrated trust, pinpointing the mistake, and progress and control — related
• AI multimodal feedback is rated higher than educator feedback on specificity, clarity, simplicity, motivation, satisfaction, and lower mental effort, with comparable correctness, trust, and acceptance — related
• Adaptive AI feedback provides tailored scaffolding and AI simulates authentic interaction scenarios (Contextual Affordance Pathway) — related
• Trust in customized agents was associated with clear, accurate, and contextually aligned feedback — related
• EFL learners perceive AI-mediated instruction as engaging, personalized, anxiety-reducing, and empowering for autonomous learning — related
• Open-ended student feedback highlighted relevance and conciseness as benefits of personalized AI videos, alongside concerns about unnaturalness, uncanny-valley discomfort, and trust — related