Intelligent Digital Assessment in Higher Education: Examining the Role of Automated Feedback in Improving Students’ Learning Progress

Intelligent digital assessment is increasingly used to provide rapid, scalable, and datainformed feedback in higher education. Yet the educational value of automated feedback
depends not only on delivery speed but also on its specificity, personalization, credibility,
and students’ willingness to act on it. This study synthesizes evidence on how automated
assessment and feedback contribute to learning progress and examines the mechanisms
through which feedback supports revision, self-regulation, and subsequent performance.
The synthesis focuses on automated assessment, automated feedback, personalized
feedback, learning analytics, writing evaluation, programming assessment, and formative
learning. The evidence indicates that automated feedback most consistently supports
immediate error identification, revision, task performance, engagement with assessment
activities, and reduced feedback delays. However, outcomes vary according to feedback
specificity, contextualization, student trust, task alignment, and opportunities for revision.
Automated systems appear particularly effective when integrated into a continuous
formative cycle rather than used solely as scoring tools. Human instructor involvement
remains important for higher-order explanation, contextual judgment, motivation, and
feedback literacy. Based on these findings, the study proposes a continuous intelligentassessment framework linking assessment data, automated diagnosis, personalized
feedback, student action, reassessment, and learning progress. The findings suggest that
effective digital assessment is best achieved by combining automated precision and
immediacy with human pedagogical judgment.