Personalized Feedback Based on Artificial Intelligence in Higher Education: Impact on the Quality of Assignment Performance

Purpose. To evaluate whether integrating generative AI into formative assessment (rubric-based feedback on course texts + an analytical progress dashboard) can improve academic performance and selfregulation of student learning in a blended course. Methodology and methods. This study presents a replicable quasi experimental study. Design: An 8-week intervention with assignment to study groups (N=312, undergraduate, 1st and 2nd years; 156 - control, 156 - intervention). The control group received traditional teacher feedback; the intervention group received structured AI feedback on the rubric with mandatory teacher moderation and individualized learning analytics in the LMS. Outcome measures: writing scores (0–100; double-blind assessment, ICC (2,1)=0.94 on 20% of items), self-regulation of learning (12 items, 1–5; α =0.88 – 0.89), cognitive load (1–9), engagement (min/week), and teacher efforts. Results. Controlling for the pretest, the intervention was associated with a 4.46-point increase in the final writing score (95% C.I. 3.25–5.68; p<0.001; Hedges’ g=0.84) and a 0.41-point increase in self-regulation (95% C.I. 0.22–0.60; p<0.001; g=0.50). Cognitive load was lower by 0.73 points (95% C.I. -1.01…-0.45; p<0.001; g= – 0.60), and engagement was higher by 22.26 minutes/week (95% C.I. 6.12–38.39; p=0.007; g=0.32). Average teacher efforts per feedback cycle was lower in the intervention (7.07±2.44 min) compared to the control (18.28±4.02 min; p<0.001). Conclusions. The combination of rubric-based AI feedback, teacher moderation, and learning analytics is a promising didactic tool for scaling up formative assessment: it improves the quality of academic writing and regulatory competencies while reducing subjective teacher workload and efforts. The methodological value of this paper is its demonstration of a full analysis cycle (protocol → data → hypothesis testing), which can be replicated and applied to data from a specific educational program.

Authors

Institutions

Publication Details

Journal
Open Education
Published
2026-11-12
DOI
https://doi.org/10.21686/1818-4243-2026-5-14-23
Primary Topic
Student Assessment and Feedback
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Personalized Feedback Based on Artificial Intelligence in Higher Education: Impact on the Quality of Assignment Performance

Unatlokov Vyacheslav Kh., Dmitry A. Usik
Open Education
Student Assessment and Feedback
article

Personalized Feedback Based on Artificial Intelligence in Higher Education: Impact on the Quality of Assignment Performance

Unatlokov Vyacheslav Kh., Dmitry A. Usik
article en

Abstract

Purpose. To evaluate whether integrating generative AI into formative assessment (rubric-based feedback on course texts + an analytical progress dashboard) can improve academic performance and selfregulation of student learning in a blended course. Methodology and methods. This study presents a replicable quasi experimental study. Design: An 8-week intervention with assignment to study groups (N=312, undergraduate, 1st and 2nd years; 156 - control, 156 - intervention). The control group received traditional teacher feedback; the intervention group received structured AI feedback on the rubric with mandatory teacher moderation and individualized learning analytics in the LMS. Outcome measures: writing scores (0–100; double-blind assessment, ICC (2,1)=0.94 on 20% of items), self-regulation of learning (12 items, 1–5; α =0.88 – 0.89), cognitive load (1–9), engagement (min/week), and teacher efforts. Results. Controlling for the pretest, the intervention was associated with a 4.46-point increase in the final writing score (95% C.I. 3.25–5.68; p<0.001; Hedges’ g=0.84) and a 0.41-point increase in self-regulation (95% C.I. 0.22–0.60; p<0.001; g=0.50). Cognitive load was lower by 0.73 points (95% C.I. -1.01…-0.45; p<0.001; g= – 0.60), and engagement was higher by 22.26 minutes/week (95% C.I. 6.12–38.39; p=0.007; g=0.32). Average teacher efforts per feedback cycle was lower in the intervention (7.07±2.44 min) compared to the control (18.28±4.02 min; p<0.001). Conclusions. The combination of rubric-based AI feedback, teacher moderation, and learning analytics is a promising didactic tool for scaling up formative assessment: it improves the quality of academic writing and regulatory competencies while reducing subjective teacher workload and efforts. The methodological value of this paper is its demonstration of a full analysis cycle (protocol → data → hypothesis testing), which can be replicated and applied to data from a specific educational program.

Open EducationVol. 30(5)
Russian State University for the Humanities (RU), Kabardino-Balkarian State University (RU)
Quality education
Student Assessment and Feedback
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon