[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-122426-en":3,"doc-seo-122426-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},122426,13056703019662,"Evangeline","https://ap-avatar.wpscdn.com/avatar/be000253a8e92610077?_k=1778726343310543188",8,"Research & Report","Evaluation of Traditional Machine Learning Algorithms for Featuring Educational Exercises","Artificial intelligence algorithms support educational environments by using machine learning to evaluate and improve education quality. This study contrasts prior work that analyzed item characteristics separately by integrating grade, number of attempts, and time from student interactions. Using 15 real educational assessments with student interaction logs (over 150 interactions per exercise), the study trained regression and classification models with varied hyperparameters. Results indicate Bayesian ridge regression and random forest regression perform best for grade prediction, while Random Forest and Nearest Neighbors stand out for classification.","Evaluation of traditional machine learning algorithms for featuring educational exercises  \nAlberto Jiménez-Macías1 · Pedro J. Muñoz-Merino1 · Pedro Manuel Moreno-Marcos1 ·  \nCarlos Delgado Kloos1  \nAccepted: 14 February 2025 © The Author(s) 2025  \nAbstract  \nArtificial intelligence (AI) algorithms are important in educational environments, and the use of machine learning algorithms to evaluate and improve the quality of education. Previous studies have individually analyzed algorithms to estimate item characteristics, such as grade, number of attempts, and time from student interactions. By contrast, this study integrated all three characteristics to discern the relationships between attempts, time, and performance in educational exercises. We analyzed 15 educational assessments using different machine learning algorithms, specifically 12 for regression and eight forclassification, with different hyperparameters. This study used real student [interaction data from Zenodo.org](interaction data from Zenodo.org), encompassing over 150 interactions per exercise, to predict grades and to improve our understanding of student performance. The results show that, in regression, the Bayesian ridge regression and random forest regression algorithms obtained the best results, and for the classification algorithms, Random Forest and Nearest Neighbors stood out. Most exercises in both scenarios involved more than 150 student interactions. Furthermore, the absence of a pattern in the variables contributes to suboptimal outcomesin some exercises. The information provided makes it more efficient to enhance the design of educational exercises.  \nKeywords Exercise modeling · Machine learning · Classification and regression · Content modeling · Learning analytics  \n1 Introduction  \nThe growth of AI in education has begun with the development of algorithms for writing and distributing tests and other applications [1] . Such algorithms have been incorporated into models that provide meaningful insights to help teachers perform better in teaching and student learning. The implications of integrating machine learning into the educational sector are vast and varied. This includes new ways to research how machine learning systems can be implemented and develop scenarios to evaluate algorithm efficiency.  \nB Alberto Jiménez-Macías [albjimen@it.uc3m.es](albjimen@it.uc3m.es)  \nPedro J. Muñoz-Merino  \n[pedmume@it.uc3m.es](pedmume@it.uc3m.es)  \nPedro Manuel Moreno-Marcos  \n[pemoreno@it.uc3m.es](pemoreno@it.uc3m.es)  \nCarlos Delgado Kloos  \n[cdk@it.uc3m.es](cdk@it.uc3m.es)  \n1 Telematic Engineering Department, Universidad Carlos III de Madrid, Av. de la Universidad, 30, Leganés 28911,  \nMadrid, Spain  \nOne major use of AI in education is Smart Learning Content (SLC) in the sense that the content should be dynamic to fit individual requirements and preferences [21] . Among the different contents, we focused on analyzing educational tests since they are exercises in which students interact with the mentioned types of content. The exercises have other tasks that the student must perform, which can involve multiple attempts, anda mark is given for each attempt. Exercise types encompass multiple choices, multiple responses, drag and drop, and open-ended problems that require manual instructor grading.  \nThe initial hypothesis of this study is that traditional machine learning algorithms can accurately model the relationship between grades, attempts, and time of students when interacting with exercises.  \nSeveral machine-learning algorithms have been used to model educational exercises. One of the most common is Item Response Theory(IRT), as indicatedby[20]. IRT allows the estimation of item characteristics, such as difficulty, discrimination, and guessing, based on student interactions. Content modeling can also be used to infer the different skills acquired by students through educational materials.  \n1 3  \nKey item characteristics recognized through the systematic lite","cbCaihAjBBI2DTki","https://ap.wps.com/l/cbCaihAjBBI2DTki","pdf",1215009,1,25,"English","en",105,"# Abstract\n# 1 Introduction\n## Smart Learning Content and educational tests\n## Research hypothesis and objectives\n## Research questions (RQ1-RQ4)","[{\"question\":\"What does the study integrate in its educational exercise modeling?\",\"answer\":\"It integrates grade, number of attempts, and time spent based on student interaction data, instead of treating these characteristics separately.\"},{\"question\":\"How many educational assessments and interaction records are used?\",\"answer\":\"The study analyzes 15 educational assessments and uses real interaction data with over 150 interactions per exercise.\"},{\"question\":\"Which algorithms achieve the best results for regression and classification?\",\"answer\":\"For regression, Bayesian ridge regression and random forest regression perform best; for classification, Random Forest and Nearest Neighbors stand out.\"}]","Evaluation of Traditional Machine Learning Algorithms for Featuring Educational Exercises | PDF",1785810558,63,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"evaluation-of-traditional-machine-learning-algorithms-for-featuring-educational-exercises","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/evaluation-of-traditional-machine-learning-algorithms-for-featuring-educational-exercises/122426/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-04",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What does the study integrate in its educational exercise modeling?","Question",{"text":75,"@type":76},"It integrates grade, number of attempts, and time spent based on student interaction data, instead of treating these characteristics separately.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How many educational assessments and interaction records are used?",{"text":80,"@type":76},"The study analyzes 15 educational assessments and uses real interaction data with over 150 interactions per exercise.",{"name":82,"@type":73,"acceptedAnswer":83},"Which algorithms achieve the best results for regression and classification?",{"text":84,"@type":76},"For regression, Bayesian ridge regression and random forest regression perform best; for classification, Random Forest and Nearest Neighbors stand out.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]