اخبار و اعلانات

 آمار

تعداد نشریات28
تعداد شماره‌ها873
تعداد مقالات8,410
تعداد مشاهده مقاله17,071,248
تعداد دریافت فایل اصل مقاله11,439,423
Aliakbarloo, Mohadeseh, Majidi, Babak, Khodabakhshi-Kolaei, Anahita. (1405). Academic Procrastination in E-Learning Environments: Assessment, Machine-Learning Classification, and an AI-Based Support Approach. نشریه علمی دانشگاه سیستان و بلوچستان, 2(3), 26-35. doi: 10.22111/ijaer.2026.57351.1056
Mohadeseh Aliakbarloo; Babak Majidi; Anahita Khodabakhshi-Kolaei. "Academic Procrastination in E-Learning Environments: Assessment, Machine-Learning Classification, and an AI-Based Support Approach". نشریه علمی دانشگاه سیستان و بلوچستان, 2, 3, 1405, 26-35. doi: 10.22111/ijaer.2026.57351.1056
Aliakbarloo, Mohadeseh, Majidi, Babak, Khodabakhshi-Kolaei, Anahita. (1405). 'Academic Procrastination in E-Learning Environments: Assessment, Machine-Learning Classification, and an AI-Based Support Approach', نشریه علمی دانشگاه سیستان و بلوچستان, 2(3), pp. 26-35. doi: 10.22111/ijaer.2026.57351.1056
Aliakbarloo, Mohadeseh, Majidi, Babak, Khodabakhshi-Kolaei, Anahita. Academic Procrastination in E-Learning Environments: Assessment, Machine-Learning Classification, and an AI-Based Support Approach. نشریه علمی دانشگاه سیستان و بلوچستان, 1405; 2(3): 26-35. doi: 10.22111/ijaer.2026.57351.1056

Academic Procrastination in E-Learning Environments: Assessment, Machine-Learning Classification, and an AI-Based Support Approach

Iranian Journal of Applied Educational Research
دوره 2، شماره 3، دی 2026، صفحه 26-35    اصل مقاله (531.05 K)
نوع مقاله: Original Article
شناسه دیجیتال (DOI): 10.22111/ijaer.2026.57351.1056
نویسندگان
Mohadeseh Aliakbarloo1؛ Babak Majidi* 2؛ Anahita Khodabakhshi-Kolaei3
1Department of Computer Engineering, Khatam University, Tehran, Iran.
2M.Sc. Student, Department of Computer Engineering, Khatam University, Tehran, Iran.
3Department of Psychology and Education, Faculty of Humanities, Khatam University, Tehran, Iran.
چکیده
This study examined academic procrastination among university students in e-learning environments, its associations with demographic and educational characteristics, and the feasibility of using machine learning and artificial intelligence to support learner analysis and intervention. Main data were obtained from 222 university students using a 22-item researcher-developed Academic Procrastination Questionnaire for E-Learning, developed from the content themes of the Solomon and Rothblum scale. Descriptive and inferential statistical procedures were used to examine procrastination and its associations with student characteristics. Decision Tree, Random Forest, and Support Vector Machine algorithms were then evaluated for auxiliary classification of procrastination into low, moderate, and high operational levels, using 49 demographic and educational features and excluding questionnaire items and derived scores to prevent information leakage. Finally, a preliminary intelligent support system was designed and evaluated through a seven-day intervention with 20 students divided into intervention and control groups. The mean academic procrastination score in the main sample was 59.57. Random Forest produced an accuracy of 0.4667 and an F1-score of 0.4697 on the held-out test set, exceeding the baseline accuracy of 0.3333. In the preliminary support evaluation, the intervention group's mean score decreased from 73.10 to 70.80, and the within-group change was statistically significant; the change also differed significantly from that of the control group. The findings support the feasibility of an integrated framework combining direct assessment, auxiliary machine learning, and intelligent support, while the small preliminary intervention sample and short duration require cautious interpretation and further evaluation in larger and longer studies.
کلیدواژه‌ها
Academic procrastination؛ E-learning؛ Artificial intelligence؛ Machine learning؛ Intelligent support system
آمار
تعداد مشاهده مقاله: 1


سامانه مدیریت نشریات علمی. طراحی و پیاده سازی از سیناوب