<?xml version="1.0" encoding="UTF-8"?>
<doi_batch version="5.3.1" xmlns="http://www.crossref.org/schema/5.3.1" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:jats="http://www.ncbi.nlm.nih.gov/JATS1" xmlns:ai="http://www.crossref.org/AccessIndicators.xsd" xsi:schemaLocation="http://www.crossref.org/schema/5.3.1 http://www.crossref.org/schema/deposit/crossref5.3.1.xsd">
 <head>
  <doi_batch_id>aspg-27-4337-1795085330</doi_batch_id>
  <timestamp>20261119104850</timestamp>
  <depositor>
   <depositor_name>American Scientific Publishing Group</depositor_name>
   <email_address>admin@americaspg.com</email_address>
  </depositor>
  <registrant>American Scientific Publishing Group</registrant>
 </head>
 <body>
  <journal>
   <journal_metadata language="en">
    <full_title>International Journal of Artificial Intelligence and Education Technology</full_title>
    <abbrev_title>IJAIET</abbrev_title>
    <issn media_type="electronic">2835-2432</issn>
   </journal_metadata>
   <journal_issue>
    <publication_date media_type="online">
     <year>2026</year>
    </publication_date>
    <journal_volume>
     <volume>5</volume>
    </journal_volume>
    <issue>1</issue>
   </journal_issue>
   <journal_article publication_type="full_text">
    <titles>
     <title>Early Identification of At-Risk Students in Virtual Learning Environments Using Ensemble Machine Learning and Behavioural Analytics</title>
    </titles>
    <contributors>
     <person_name sequence="first" contributor_role="author">
      <given_name>Ahmed Abd El-Badie Abd Allah</given_name>
      <surname>Kamel</surname>
      <affiliations>
       <institution>
        <institution_name>Associate Professor of Computer Science and the Director of the Monitoring and Technical Support Unit at the Measurement and Evaluation Center, Mansoura University, Egypt</institution_name>
       </institution>
      </affiliations>
     </person_name>
    </contributors>
    <jats:abstract>
     <jats:p>Identifying students at risk of academic failure or course withdrawal early in their enrolment remains a major challenge in higher and distance education. This study evaluates seven machine-learning classifiers for early risk prediction using an OULAD-inspired dataset of 7,895 student records, with eight demographic and administrative features and eight Virtual Learning Environment (VLE) engagement features. Models were assessed using five-fold stratified cross-validation. Logistic Regression achieved the highest mean AUC-ROC (0.786), AdaBoost the highest mean accuracy (0.716), and Gradient Boosting Decision Tree (GBDT) the highest mean recall (0.769). GBDT also achieved an AUC-ROC of 0.782 (± 0.003), accuracy of 0.708 (± 0.005), and F1-score of 0.729 (± 0.006). Gini-based feature importance identified late submissions (0.304), total VLE clicks (0.150), and first assessment score (0.135) as the strongest predictors. These results suggest that early learning-management-system traces can support timely student outreach, while also underscoring the need for equitable, human-led use of predictive analytics.</jats:p>
    </jats:abstract>
    <publication_date media_type="online">
     <year>2026</year>
    </publication_date>
    <pages>
     <first_page>18</first_page>
     <last_page>24</last_page>
    </pages>
    <publisher_item>
     <item_number item_number_type="article-number">4337</item_number>
    </publisher_item>
    <ai:program name="AccessIndicators">
     <ai:license_ref applies_to="vor">https://creativecommons.org/licenses/by/4.0/</ai:license_ref>
    </ai:program>
    <doi_data>
     <doi>10.54216/IJAIET.050103</doi>
     <resource>http://demo.americaspg.com/journal/27/article/4337</resource>
     <collection property="text-mining">
      <item>
       <resource mime_type="application/pdf">http://demo.americaspg.com/storage/articles/manuscripts/01M7GGAJMVRRDZ556FQAQ3WBY0.pdf</resource>
      </item>
     </collection>
    </doi_data>
   </journal_article>
  </journal>
 </body>
</doi_batch>
