Personalized Learning in K-12 Education: Exploring Weak-Labels for a Random Forest-based Collaborative Filtering Approach. Ilídio, P., Gharahighehi, A., Nakano, F. K., & Vens, C. CEUR Workshop Proceedings, 3836:38–48, 2024. ISBN: 0000000248abstract bibtex Education, a cornerstone of human development, increasingly leverages digital learning tools, generating valuable data from student interactions. This data can enhance learning efficiency through adaptive and personalized systems, moving beyond the traditional "one-size-fits-all" model. Recommendation systems learn user profiles to suggest relevant items and personalize students’ learning experiences. In the context of implicit feedback, binary interactions are used in weak-label learning, where negative label annotations are unreliable. This paper proposes a weak-label learning method for recommending learning materials and trajectories, combining local and global Random Forests in a multi-step collaborative filtering process. The proposed approach is named PentaForest, and outperforms other popular collaborative filtering methods in terms of NDCG and recall.
@article{ilidio_personalized_2024,
title = {Personalized {Learning} in {K}-12 {Education}: {Exploring} {Weak}-{Labels} for a {Random} {Forest}-based {Collaborative} {Filtering} {Approach}},
volume = {3836},
issn = {16130073},
abstract = {Education, a cornerstone of human development, increasingly leverages digital learning tools, generating valuable data from student interactions. This data can enhance learning efficiency through adaptive and personalized systems, moving beyond the traditional "one-size-fits-all" model. Recommendation systems learn user profiles to suggest relevant items and personalize students’ learning experiences. In the context of implicit feedback, binary interactions are used in weak-label learning, where negative label annotations are unreliable. This paper proposes a weak-label learning method for recommending learning materials and trajectories, combining local and global Random Forests in a multi-step collaborative filtering process. The proposed approach is named PentaForest, and outperforms other popular collaborative filtering methods in terms of NDCG and recall.},
journal = {CEUR Workshop Proceedings},
author = {Ilídio, Pedro and Gharahighehi, Alireza and Nakano, Felipe Kenji and Vens, Celine},
year = {2024},
note = {ISBN: 0000000248},
keywords = {Random Forest, collaborative filtering, educational recommendation, k-12 education, weak-label learning},
pages = {38--48},
}
Downloads: 0
{"_id":"2LJo2w9rQNGYsJgop","bibbaseid":"ildio-gharahighehi-nakano-vens-personalizedlearningink12educationexploringweaklabelsforarandomforestbasedcollaborativefilteringapproach-2024","author_short":["Ilídio, P.","Gharahighehi, A.","Nakano, F. K.","Vens, C."],"bibdata":{"bibtype":"article","type":"article","title":"Personalized Learning in K-12 Education: Exploring Weak-Labels for a Random Forest-based Collaborative Filtering Approach","volume":"3836","issn":"16130073","abstract":"Education, a cornerstone of human development, increasingly leverages digital learning tools, generating valuable data from student interactions. This data can enhance learning efficiency through adaptive and personalized systems, moving beyond the traditional \"one-size-fits-all\" model. Recommendation systems learn user profiles to suggest relevant items and personalize students’ learning experiences. In the context of implicit feedback, binary interactions are used in weak-label learning, where negative label annotations are unreliable. This paper proposes a weak-label learning method for recommending learning materials and trajectories, combining local and global Random Forests in a multi-step collaborative filtering process. The proposed approach is named PentaForest, and outperforms other popular collaborative filtering methods in terms of NDCG and recall.","journal":"CEUR Workshop Proceedings","author":[{"propositions":[],"lastnames":["Ilídio"],"firstnames":["Pedro"],"suffixes":[]},{"propositions":[],"lastnames":["Gharahighehi"],"firstnames":["Alireza"],"suffixes":[]},{"propositions":[],"lastnames":["Nakano"],"firstnames":["Felipe","Kenji"],"suffixes":[]},{"propositions":[],"lastnames":["Vens"],"firstnames":["Celine"],"suffixes":[]}],"year":"2024","note":"ISBN: 0000000248","keywords":"Random Forest, collaborative filtering, educational recommendation, k-12 education, weak-label learning","pages":"38–48","bibtex":"@article{ilidio_personalized_2024,\n\ttitle = {Personalized {Learning} in {K}-12 {Education}: {Exploring} {Weak}-{Labels} for a {Random} {Forest}-based {Collaborative} {Filtering} {Approach}},\n\tvolume = {3836},\n\tissn = {16130073},\n\tabstract = {Education, a cornerstone of human development, increasingly leverages digital learning tools, generating valuable data from student interactions. This data can enhance learning efficiency through adaptive and personalized systems, moving beyond the traditional \"one-size-fits-all\" model. Recommendation systems learn user profiles to suggest relevant items and personalize students’ learning experiences. In the context of implicit feedback, binary interactions are used in weak-label learning, where negative label annotations are unreliable. This paper proposes a weak-label learning method for recommending learning materials and trajectories, combining local and global Random Forests in a multi-step collaborative filtering process. The proposed approach is named PentaForest, and outperforms other popular collaborative filtering methods in terms of NDCG and recall.},\n\tjournal = {CEUR Workshop Proceedings},\n\tauthor = {Ilídio, Pedro and Gharahighehi, Alireza and Nakano, Felipe Kenji and Vens, Celine},\n\tyear = {2024},\n\tnote = {ISBN: 0000000248},\n\tkeywords = {Random Forest, collaborative filtering, educational recommendation, k-12 education, weak-label learning},\n\tpages = {38--48},\n}\n\n\n\n","author_short":["Ilídio, P.","Gharahighehi, A.","Nakano, F. K.","Vens, C."],"key":"ilidio_personalized_2024","id":"ilidio_personalized_2024","bibbaseid":"ildio-gharahighehi-nakano-vens-personalizedlearningink12educationexploringweaklabelsforarandomforestbasedcollaborativefilteringapproach-2024","role":"author","urls":{},"keyword":["Random Forest","collaborative filtering","educational recommendation","k-12 education","weak-label learning"],"metadata":{"authorlinks":{}},"html":""},"bibtype":"article","biburl":"https://bibbase.org/zotero/jumoga","dataSources":["NWfDysABGA323queN"],"keywords":["random forest","collaborative filtering","educational recommendation","k-12 education","weak-label learning"],"search_terms":["personalized","learning","education","exploring","weak","labels","random","forest","based","collaborative","filtering","approach","ilídio","gharahighehi","nakano","vens"],"title":"Personalized Learning in K-12 Education: Exploring Weak-Labels for a Random Forest-based Collaborative Filtering Approach","year":2024}