Methodology for the analysis of student behavior and performance in an online course
Although many researchers have studied student performance prediction in online courses, they have primarily focused on courses with a linear structure, where students complete lessons and assessments sequentially. However, non-linear courses allow students to take lessons and assessments in any ord...
- Autores:
-
Mercado Agudelo, Jhon Fredy
- Tipo de recurso:
- Fecha de publicación:
- 2025
- Institución:
- Universidad de Antioquia
- Repositorio:
- Repositorio UdeA
- Idioma:
- eng
- OAI Identifier:
- oai:bibliotecadigital.udea.edu.co:10495/46166
- Acceso en línea:
- https://hdl.handle.net/10495/46166
- Palabra clave:
- Machine learning
Aprendizaje automático
Data mining
MOOCs (Web-based instruction)
Cursos en línea masivos en abierto
Student Performance Prediction
http://id.loc.gov/authorities/subjects/sh85079324
http://id.loc.gov/authorities/subjects/sh97002073
http://id.loc.gov/authorities/subjects/sh2013002540
- Rights
- openAccess
- License
- http://creativecommons.org/licenses/by-nc-sa/4.0/
| id |
UDEA2_764ec0c284db740b228a5f1751a254f9 |
|---|---|
| oai_identifier_str |
oai:bibliotecadigital.udea.edu.co:10495/46166 |
| network_acronym_str |
UDEA2 |
| network_name_str |
Repositorio UdeA |
| repository_id_str |
|
| dc.title.eng.fl_str_mv |
Methodology for the analysis of student behavior and performance in an online course |
| dc.title.translated.none.fl_str_mv |
Metodología para el análisis del comportamiento y el desempeño de los estudiantes en un curso en línea |
| title |
Methodology for the analysis of student behavior and performance in an online course |
| spellingShingle |
Methodology for the analysis of student behavior and performance in an online course Machine learning Aprendizaje automático Data mining MOOCs (Web-based instruction) Cursos en línea masivos en abierto Student Performance Prediction http://id.loc.gov/authorities/subjects/sh85079324 http://id.loc.gov/authorities/subjects/sh97002073 http://id.loc.gov/authorities/subjects/sh2013002540 |
| title_short |
Methodology for the analysis of student behavior and performance in an online course |
| title_full |
Methodology for the analysis of student behavior and performance in an online course |
| title_fullStr |
Methodology for the analysis of student behavior and performance in an online course |
| title_full_unstemmed |
Methodology for the analysis of student behavior and performance in an online course |
| title_sort |
Methodology for the analysis of student behavior and performance in an online course |
| dc.creator.fl_str_mv |
Mercado Agudelo, Jhon Fredy |
| dc.contributor.advisor.none.fl_str_mv |
Gaviria Gómez, Natalia Mendoza Cardenas, Carlos Henry |
| dc.contributor.author.none.fl_str_mv |
Mercado Agudelo, Jhon Fredy |
| dc.contributor.researchgroup.none.fl_str_mv |
Grupo de Investigación en Telecomunicaciones Aplicadas (GITA) |
| dc.contributor.jury.none.fl_str_mv |
Duitama Muñoz, John Freddy Isaza Ramirez, Sebastian |
| dc.subject.lcsh.none.fl_str_mv |
Machine learning Aprendizaje automático Data mining MOOCs (Web-based instruction) Cursos en línea masivos en abierto |
| topic |
Machine learning Aprendizaje automático Data mining MOOCs (Web-based instruction) Cursos en línea masivos en abierto Student Performance Prediction http://id.loc.gov/authorities/subjects/sh85079324 http://id.loc.gov/authorities/subjects/sh97002073 http://id.loc.gov/authorities/subjects/sh2013002540 |
| dc.subject.proposal.eng.fl_str_mv |
Student Performance Prediction |
| dc.subject.lcshuri.none.fl_str_mv |
http://id.loc.gov/authorities/subjects/sh85079324 http://id.loc.gov/authorities/subjects/sh97002073 http://id.loc.gov/authorities/subjects/sh2013002540 |
| description |
Although many researchers have studied student performance prediction in online courses, they have primarily focused on courses with a linear structure, where students complete lessons and assessments sequentially. However, non-linear courses allow students to take lessons and assessments in any order, making performance prediction more challenging due to varying cumulative assessment percentages among students at any given time. This master's thesis aims to develop a data-driven method for early student performance prediction in non-linear courses. We created a feature extractor and evaluated three types of features: engagement, behavior, and performance. The data comes from Moodle courses designed to prepare high school students for a public university entrance exam. Our method achieved early predictions at 20% of cumulative weight assessment with an F1-score of 0.73 for binary classification and an R² of 0.40 for regression. We also conducted a feature importance analysis, showing that performance and behavior features are the most significant predictors, with engagement features, such as time spent on educational resources, also contributing significantly. In addition to predicting student performance, we performed a clustering analysis and identified four patterns that consistently appear across various cumulative weight assessments. These patterns significantly impact performance and can help educators provide better feedback and more personalized attention to students' needs. |
| publishDate |
2025 |
| dc.date.accessioned.none.fl_str_mv |
2025-05-29T15:43:33Z |
| dc.date.issued.none.fl_str_mv |
2025 |
| dc.type.none.fl_str_mv |
Trabajo de grado - Maestría |
| dc.type.redcol.none.fl_str_mv |
http://purl.org/redcol/resource_type/TM |
| dc.type.content.none.fl_str_mv |
Text |
| dc.type.coarversion.none.fl_str_mv |
http://purl.org/coar/version/c_b1a7d7d4d402bcce |
| dc.type.driver.none.fl_str_mv |
info:eu-repo/semantics/masterThesis |
| dc.type.version.none.fl_str_mv |
info:eu-repo/semantics/draft |
| status_str |
draft |
| dc.identifier.citation.none.fl_str_mv |
J. F. Mercado Agudelo, “Methodology for the analysis of student behavior and performance in an online course.”, Tesis de maestría, Maestría en Ingeniería de Telecomunicaciones, Universidad de Antioquia, Medellín, Antioquia, Colombia, 2025. |
| dc.identifier.uri.none.fl_str_mv |
https://hdl.handle.net/10495/46166 |
| identifier_str_mv |
J. F. Mercado Agudelo, “Methodology for the analysis of student behavior and performance in an online course.”, Tesis de maestría, Maestría en Ingeniería de Telecomunicaciones, Universidad de Antioquia, Medellín, Antioquia, Colombia, 2025. |
| url |
https://hdl.handle.net/10495/46166 |
| dc.language.iso.none.fl_str_mv |
eng |
| language |
eng |
| dc.relation.references.none.fl_str_mv |
@article{ellis2009learning, title={Learning management systems}, author={Ellis, Ryann K}, journal={Alexandria, VI: American Society for Training \& Development (ASTD)}, year={2009} } @inproceedings{llamas2011useoflms, title={Use of LMS functionalities in engineering education}, author={Llamas, Mart{\\i}n and Caeiro, Manuel and Castro, Manuel and Plaza, Inmaculada and Tovar, Edmundo}, booktitle={2011 Frontiers in Education Conference (FIE)}, pages={S1G--1}, year={2011}, organization={IEEE} } @article{chen2014ahybrid, title={A hybrid recommendation algorithm adapted in e-learning environments}, author={Chen, Wei and Niu, Zhendong and Zhao, Xiangyu and Li, Yi}, journal={World Wide Web}, volume={17}, number={2}, pages={271--284}, year={2014}, publisher={Springer} } @article{seo2021analysis, title={Analysis of LMS Data of Distance Lifelong Learning Center Learners and Drop-out Prediction}, author={Seo, Jong-Taek and Park, Bok-Nyong and Kim, Young-gi and Yeon, Ko-Woon}, journal={Journal of Human-centric Science and Technology Innovation}, volume={1}, number={3}, pages={23--32}, year={2021} } @incollection{mobasher2007data, title={Data mining for web personalization}, author={Mobasher, Bamshad}, booktitle={The adaptive web}, pages={90--135}, year={2007}, publisher={Springer} } @article{conijn2016predicting, title={Predicting student performance from LMS data: A comparison of 17 blended courses using Moodle LMS}, author={Conijn, Rianne and Snijders, Chris and Kleingeld, Ad and Matzat, Uwe}, journal={IEEE Transactions on Learning Technologies}, volume={10}, number={1}, pages={17--29}, year={2016}, publisher={IEEE} } @article{hooshyar2019mining, title={Mining educational data to predict students’ performance through procrastination behavior}, author={Hooshyar, Danial and Pedaste, Margus and Yang, Yeongwook}, journal={Entropy}, volume={22}, number={1}, pages={12}, year={2019}, publisher={MDPI} } @article{tamada2022predicting, title={Predicting students at risk of dropout in technical course using LMS logs}, author={Tamada, Mariela Mizota and Giusti, Rafael and Netto, Jos{\e} Francisco de Magalh{\~a}es}, journal={Electronics}, volume={11}, number={3}, pages={468}, year={2022}, publisher={MDPI} } @article{cerezo2016students, title={Students LMS interaction patterns and their relationship with achievement: A case study in higher education}, author={Cerezo, Rebeca and S{\a}nchez-Santill{\a}n, Miguel and Paule-Ruiz, M Puerto and N{\u}{\~n}ez, J Carlos}, journal={Computers \& Education}, volume={96}, pages={42--54}, year={2016}, publisher={Elsevier} } @article{macfadyen2010mining, title={Mining LMS data to develop an “early warning system” for educators: A proof of concept}, author={Macfadyen, Leah P and Dawson, Shane}, journal={Computers \& education}, volume={54}, number={2}, pages={588--599}, year={2010}, publisher={Elsevier} } @article{tomasevic2020anoverview, title={An overview and comparison of supervised data mining techniques for student exam performance prediction}, author={Tomasevic, Nikola and Gvozdenovic, Nikola and Vranes, Sanja}, journal={Computers \& education}, volume={143}, pages={103676}, year={2020}, publisher={Elsevier} } @article{ljubobratovic2019using, title={Using LMS Activity Logs to Predict Student Failure with Random Forest Algorithm}, author={Ljubobratovi{\c}, Dejan and Mateti{\c}, Maja}, journal={The Future of Information Sciences}, pages={113}, year={2019} } @article{riestra2021massive, title={Massive LMS log data analysis for the early prediction of course-agnostic student performance}, author={Riestra-Gonz{\a}lez, Moises and del Puerto Paule-Ru{\\i}z, Maria and Ortin, Francisco}, journal={Computers \& Education}, volume={163}, pages={104108}, year={2021}, publisher={Elsevier} } @inproceedings{tamada2021predicting, title={Predicting student performance based on logs in moodle LMS}, author={Tamada, Mariela Mizota and Giusti, Rafael and de Magalh{\~a}es Netto, Jos{\e} Francisco}, booktitle={2021 IEEE Frontiers in Education Conference (FIE)}, pages={1--8}, year={2021}, organization={IEEE} } @article{lopez2020towards, title={Towards portability of models for predicting students’ final performance in university courses starting from moodle logs}, author={L{\o}pez-Zambrano, Javier and Lara, Juan A and Romero, Cristobal}, journal={Applied Sciences}, volume={10}, number={1}, pages={354}, year={2020}, publisher={MDPI} } @article{jokhan2019early, title={Early warning system as a predictor for student performance in higher education blended courses}, author={Jokhan, Anjeela and Sharma, Bibhya and Singh, Shaveen}, journal={Studies in Higher Education}, volume={44}, number={11}, pages={1900--1911}, year={2019}, publisher={Taylor \& Francis} } @misc{moodle2024, title = {Moodle Database schema}, howpublished = {\url{https://moodledev.io/docs/apis/core/dml/database-schema}}, note = {Accessed: 2024} } @article{romero2020educational, title={Educational data mining and learning analytics: An updated survey}, author={Romero, Cristobal and Ventura, Sebastian}, journal={Wiley interdisciplinary reviews: Data mining and knowledge discovery}, volume={10}, number={3}, pages={e1355}, year={2020}, publisher={Wiley Online Library} } @article{ray2018applications, title={Applications of educational data mining and learning analytics tools in handling big data in higher education}, author={Ray, Santosh and Saeed, Mohammed}, journal={Applications of Big Data analytics: Trends, issues, and challenges}, pages={135--160}, year={2018}, publisher={Springer} } @inproceedings{kloft2014predicting, title={Predicting MOOC dropout over weeks using machine learning methods}, author={Kloft, Marius and Stiehler, Felix and Zheng, Zhilin and Pinkwart, Niels}, booktitle={Proceedings of the EMNLP 2014 workshop on analysis of large scale social interaction in MOOCs}, pages={60--65}, year={2014} } @article{nordin2015tecnhology, title={Technology acceptance of massive open online courses in Malaysia.}, author={Nordin, Norazah and Norman, Helmi and Embi, Mohamad Amin}, journal={Malaysian Journal of Distance Education}, volume={17}, number={2}, year={2015} } @article{nabizadeh2020adaptive, title={Adaptive learning path recommender approach using auxiliary learning objects}, author={Nabizadeh, Amir Hossein and Goncalves, Daniel and Gama, Sandra and Jorge, Joaquim and Rafsanjani, Hamed N}, journal={Computers \& Education}, volume={147}, pages={103777}, year={2020}, publisher={Elsevier} } @article{alsadoon2020theimpact, title={The impact of an adaptive e-course on students’ achievements based on the students’ prior knowledge}, author={Alsadoon, Elham}, journal={Education and information technologies}, volume={25}, number={5}, pages={3541--3551}, year={2020}, publisher={Springer} } @article{chen2018recommendation, title={Recommendation system for adaptive learning}, author={Chen, Yunxiao and Li, Xiaoou and Liu, Jingchen and Ying, Zhiliang}, journal={Applied psychological measurement}, volume={42}, number={1}, pages={24--41}, year={2018}, publisher={Sage Publications Sage CA: Los Angeles, CA} } @inproceedings{mercado2023work, title={Work in progress: A didactic strategy based on Machine Learning for adaptive learning in virtual environments}, author={Mercado, Jhon and Mendoza, Carlos H and Ramirez-Salazar, Doris A and Valderrama, Angela and Gaviria-Gomez, Natalia and Botero, Juan F and Fletscher, Luis}, booktitle={2023 IEEE World Engineering Education Conference (EDUNINE)}, pages={1--4}, year={2023}, organization={IEEE} } @article{adnan2021predicting, title={Predicting at-risk students at different percentages of course length for early intervention using machine learning models}, author={Adnan, Muhammad and Habib, Asad and Ashraf, Jawad and Mussadiq, Shafaq and Raza, Arsalan Ali and Abid, Muhammad and Bashir, Maryam and Khan, Sana Ullah}, journal={Ieee Access}, volume={9}, pages={7519--7539}, year={2021}, publisher={IEEE} } @article{kuzilek2017open, title={Open university learning analytics dataset}, author={Kuzilek, Jakub and Hlosta, Martin and Zdrahal, Zdenek}, journal={Scientific data}, volume={4}, number={1}, pages={1--8}, year={2017}, publisher={Nature Publishing Group} } @article{cohausz2023investigating, title={Investigating the Importance of Demographic Features for EDM-Predictions.}, author={Cohausz, Lea and Tschalzev, Andrej and Bartelt, Christian and Stuckenschmidt, Heiner}, journal={International Educational Data Mining Society}, year={2023}, publisher={ERIC} } @article{hoq2023analysis, title={Analysis of an Explainable Student Performance Prediction Model in an Introductory Programming Course.}, author={Hoq, Muntasir and Brusilovsky, Peter and Akram, Bita}, journal={International Educational Data Mining Society}, year={2023}, publisher={ERIC} } @inproceedings{rohani2023early, title={Early prediction of student performance in a health data science MOOC}, author={Rohani, Narjes and Gal, Kobi and Gallagher, Michael and Manataki, Areti}, booktitle={Proceedings of the 16th International Conference on Educational Data Mining}, year={2023}, organization={International Educational Data Mining Society} } @inproceedings{mao2022cross, title={Cross-lingual adversarial domain adaptation for novice programming}, author={Mao, Ye and Khoshnevisan, Farzaneh and Price, Thomas and Barnes, Tiffany and Chi, Min}, booktitle={Proceedings of the AAAI Conference on Artificial Intelligence}, volume={36}, number={7}, pages={7682--7690}, year={2022} } @article{lundberg2017unified, title={A unified approach to interpreting model predictions}, author={Lundberg, Scott M and Lee, Su-In}, journal={Advances in neural information processing systems}, volume={30}, year={2017} } @article{cenka2022analysing, title={Analysing student behaviour in a learning management system using a process mining approach.}, author={Cenka, Baginda Anggun Nan and Santoso, Harry B and Junus, Kasiyah}, journal={Knowledge Management \& E-Learning}, volume={14}, number={1}, pages={62--80}, year={2022}, publisher={ERIC} } @article{bessadok2023exploring, title={Exploring students digital activities and performances through their activities logged in learning management system using educational data mining approach}, author={Bessadok, Adel and Abouzinadah, Ehab and Rabie, Osama}, journal={Interactive Technology and Smart Education}, volume={20}, number={1}, pages={58--72}, year={2023}, publisher={Emerald Publishing Limited} } @book{joshi2016ML, title={Python machine learning cookbook}, author={Joshi, Prateek}, year={2016}, publisher={Packt Publishing Ltd} } @article{cawley2010over, title={On over-fitting in model selection and subsequent selection bias in performance evaluation}, author={Cawley, Gavin C and Talbot, Nicola LC}, journal={The Journal of Machine Learning Research}, volume={11}, pages={2079--2107}, year={2010}, publisher={JMLR. org} } @article{Li2018Technology, title={Technology tools in distance education: A review of faculty adoption}, author={Li, Rui and Singh, JT and Bunk, Jennifer}, journal={EdMedia+ Innovate Learning}, pages={1982--1987}, year={2018}, publisher={Association for the Advancement of Computing in Education (AACE)} } @article{Hew2014Students, title={Students’ and instructors’ use of massive open online courses (MOOCs): Motivations and challenges}, author={Hew, Khe Foon and Cheung, Wing Sum}, journal={Educational research review}, volume={12}, pages={45--58}, year={2014}, publisher={Elsevier} } @inproceedings{morales2014telescope, title={Telescope, a MOOCs initiative in latin America: Infrastructure, best practices, completion and dropout analysis}, author={Morales, Miguel and Rizzardini, Rocael Hern{\a}ndez and G{\"u}tl, Christian}, booktitle={2014 IEEE Frontiers in Education Conference (FIE) Proceedings}, pages={1--7}, year={2014}, organization={IEEE} } @misc{udea_virtual_2024, author = {Ude@ Educación Virtual}, title = {Ude@ Educación Virtual}, howpublished = {\url{https://udearroba.udea.edu.co/home/}}, year = 2024, } @article{anderson2005search, title={The search for learning community in learner paced distance education: Or,Having your cake and eating it, too!}, author={Anderson, Terry and Annand, David and Wark, Norine}, journal={Australasian Journal of Educational Technology}, volume={21}, number={2}, year={2005} } @inproceedings{gao2021early, title={Early performance prediction using interpretable patterns in programming process data}, author={Gao, Ge and Marwan, Samiha and Price, Thomas W}, booktitle={Proceedings of the 52nd ACM technical symposium on computer science education}, pages={342--348}, year={2021} } @article{gamage2022systematic, title={A systematic review on trends in using Moodle for teaching and learning}, author={Gamage, Sithara HPW and Ayres, Jennifer R and Behrend, Monica B}, journal={International journal of STEM education}, volume={9}, number={1}, pages={9}, year={2022}, publisher={Springer} } @article{bradley2021learning, title={Learning Management System (LMS) use with online instruction.}, author={Bradley, Vaughn Malcolm}, journal={International Journal of Technology in Education}, volume={4}, number={1}, pages={68--92}, year={2021}, publisher={ERIC} } @article{badali2022role, title={The role of motivation in MOOCs’ retention rates: a systematic literature review}, author={Badali, Mehdi and Hatami, Javad and Banihashem, Seyyed Kazem and Rahimi, Ebrahim and Noroozi, Omid and Eslami, Zahra}, journal={Research and Practice in Technology Enhanced Learning}, volume={17}, number={1}, pages={5}, year={2022}, publisher={Springer} } @article{wang2023factors, title={Factors of dropout from MOOCs: a bibliometric review}, author={Wang, Wei and Zhao, Yongyong and Wu, Yenchun Jim and Goh, Mark}, journal={Library Hi Tech}, volume={41}, number={2}, pages={432--453}, year={2023}, publisher={Emerald Publishing Limited} } @article{polyzou2019feature, title={Feature extraction for next-term prediction of poor student performance}, author={Polyzou, Agoritsa and Karypis, George}, journal={IEEE Transactions on Learning Technologies}, volume={12}, number={2}, pages={237--248}, year={2019}, publisher={IEEE} } @article{ulitzsch2021combining, title={Combining clickstream analyses and graph-modeled data clustering for identifying common response processes}, author={Ulitzsch, Esther and He, Qiwei and Ulitzsch, Vincent and Molter, Hendrik and Nichterlein, Andr{\e} and Niedermeier, Rolf and Pohl, Steffi}, journal={psychometrika}, volume={86}, number={1}, pages={190--214}, year={2021}, publisher={Springer} } @online{moodleDatabaseSchema, author = "{Moodle Docs}", title = "{Database schema introduction}", year = "n.d.", url = "https://docs.moodle.org/dev/Database_schema_introduction", organization = "{Moodle Docs}", } @inproceedings{siemens2012learning, title={Learning analytics and educational data mining: towards communication and collaboration}, author={Siemens, George and Baker, Ryan SJ d}, booktitle={Proceedings of the 2nd international conference on learning analytics and knowledge}, pages={252--254}, year={2012} } @inproceedings{guo2014video, title={How video production affects student engagement: An empirical study of MOOC videos}, author={Guo, Philip J and Kim, Juho and Rubin, Rob}, booktitle={Proceedings of the first ACM conference on Learning scale conference}, pages={41--50}, year={2014} } @incollection{lecun2002efficient, title={Efficient backprop}, author={LeCun, Yann and Bottou, L{\e}on and Orr, Genevieve B and M{\"u}ller, Klaus-Robert}, booktitle={Neural networks: Tricks of the trade}, pages={9--50}, year={2002}, publisher={Springer} } @book{bishop2006pattern, title={Pattern recognition and machine learning}, author={Bishop, Christopher M and Nasrabadi, Nasser M}, volume={4}, number={4}, year={2006}, publisher={Springer} } @article{kim2017understanding, title={Understanding one-way ANOVA using conceptual figures}, author={Kim, Tae Kyun}, journal={Korean journal of anesthesiology}, volume={70}, number={1}, pages={22}, year={2017}, publisher={Korean Society of Anesthesiologists} } @article{scikit-learn, title={Scikit-learn: Machine Learning in {P}ython}, author={Pedregosa, F. and Varoquaux, G. and Gramfort, A. and Michel, V. and Thirion, B. and Grisel, O. and Blondel, M. and Prettenhofer, P. and Weiss, R. and Dubourg, V. and Vanderplas, J. and Passos, A. and Cournapeau, D. and Brucher, M. and Perrot, M. and Duchesnay, E.}, journal={Journal of Machine Learning Research}, volume={12}, pages={2825--2830}, year={2011} } @article{saarela2021comparison, title={Comparison of feature importance measures as explanations for classification models}, author={Saarela, Mirka and Jauhiainen, Susanne}, journal={SN Applied Sciences}, volume={3}, number={2}, pages={272}, year={2021}, publisher={Springer} } @inproceedings{trivedi2011clustering, title={Clustering students to generate an ensemble to improve standard test score predictions}, author={Trivedi, Shubhendu and Pardos, Zachary A and Heffernan, Neil T}, booktitle={Artificial Intelligence in Education: 15th International Conference, AIED 2011, Auckland, New Zealand, June 28--July 2011 15}, pages={377--384}, year={2011}, organization={Springer} } @article{alsariera2022assessment, title={Assessment and evaluation of different machine learning algorithms for predicting student performance}, author={Alsariera, Yazan A and Baashar, Yahia and Alkawsi, Gamal and Mustafa, Abdulsalam and Alkahtani, Ammar Ahmed and Ali, Norashikin}, journal={Computational Intelligence and Neuroscience}, volume={2022}, year={2022}, publisher={Hindawi Limited} } |
| dc.rights.uri.none.fl_str_mv |
http://creativecommons.org/licenses/by-nc-sa/4.0/ |
| dc.rights.accessrights.none.fl_str_mv |
info:eu-repo/semantics/openAccess |
| dc.rights.license.en.fl_str_mv |
Attribution-NonCommercial-ShareAlike 4.0 International |
| dc.rights.coar.none.fl_str_mv |
http://purl.org/coar/access_right/c_abf2 |
| rights_invalid_str_mv |
http://creativecommons.org/licenses/by-nc-sa/4.0/ Attribution-NonCommercial-ShareAlike 4.0 International http://purl.org/coar/access_right/c_abf2 |
| eu_rights_str_mv |
openAccess |
| dc.format.extent.none.fl_str_mv |
67 páginas |
| dc.format.mimetype.none.fl_str_mv |
application/pdf |
| dc.publisher.none.fl_str_mv |
Universidad de Antioquia |
| dc.publisher.program.none.fl_str_mv |
Maestría en Ingeniería de Telecomunicaciones |
| dc.publisher.faculty.none.fl_str_mv |
Facultad de Ingeniería |
| dc.publisher.branch.none.fl_str_mv |
Campus Medellín - Ciudad Universitaria |
| publisher.none.fl_str_mv |
Universidad de Antioquia |
| institution |
Universidad de Antioquia |
| bitstream.url.fl_str_mv |
https://bibliotecadigital.udea.edu.co/bitstreams/a74c600d-5002-4a62-a8f6-443099d6126a/download https://bibliotecadigital.udea.edu.co/bitstreams/e7e80f1b-1af4-4e8d-8ff6-44b982f6fc51/download https://bibliotecadigital.udea.edu.co/bitstreams/f34f4e84-3064-4ce4-beef-6f23ef86e20e/download https://bibliotecadigital.udea.edu.co/bitstreams/7fd76184-b916-4477-8337-cc6a6e07db1a/download https://bibliotecadigital.udea.edu.co/bitstreams/aeb8f047-74c7-4a28-8774-0be2b2919fd8/download |
| bitstream.checksum.fl_str_mv |
78e3bf52652ce39b0a9062aac086cf95 5643bfd9bcf29d560eeec56d584edaa9 b76e7a76e24cf2f94b3ce0ae5ed275d0 2d29f08a30ed5cd66bc2313df293efa2 96879fe5e4f8b698e8a41791b4c1e1bf |
| bitstream.checksumAlgorithm.fl_str_mv |
MD5 MD5 MD5 MD5 MD5 |
| repository.name.fl_str_mv |
Repositorio Institucional de la Universidad de Antioquia |
| repository.mail.fl_str_mv |
aplicacionbibliotecadigitalbiblioteca@udea.edu.co |
| _version_ |
1851052287469813760 |
| spelling |
Gaviria Gómez, NataliaMendoza Cardenas, Carlos HenryMercado Agudelo, Jhon FredyGrupo de Investigación en Telecomunicaciones Aplicadas (GITA)Duitama Muñoz, John FreddyIsaza Ramirez, Sebastian2025-05-29T15:43:33Z2025J. F. Mercado Agudelo, “Methodology for the analysis of student behavior and performance in an online course.”, Tesis de maestría, Maestría en Ingeniería de Telecomunicaciones, Universidad de Antioquia, Medellín, Antioquia, Colombia, 2025.https://hdl.handle.net/10495/46166Although many researchers have studied student performance prediction in online courses, they have primarily focused on courses with a linear structure, where students complete lessons and assessments sequentially. However, non-linear courses allow students to take lessons and assessments in any order, making performance prediction more challenging due to varying cumulative assessment percentages among students at any given time. This master's thesis aims to develop a data-driven method for early student performance prediction in non-linear courses. We created a feature extractor and evaluated three types of features: engagement, behavior, and performance. The data comes from Moodle courses designed to prepare high school students for a public university entrance exam. Our method achieved early predictions at 20% of cumulative weight assessment with an F1-score of 0.73 for binary classification and an R² of 0.40 for regression. We also conducted a feature importance analysis, showing that performance and behavior features are the most significant predictors, with engagement features, such as time spent on educational resources, also contributing significantly. In addition to predicting student performance, we performed a clustering analysis and identified four patterns that consistently appear across various cumulative weight assessments. These patterns significantly impact performance and can help educators provide better feedback and more personalized attention to students' needs.Aunque muchos investigadores han estudiado la predicción del rendimiento de los estudiantes en cursos en línea, se han centrado principalmente en cursos con una estructura lineal, en los que los estudiantes completan las lecciones y las evaluaciones de forma secuencial. Sin embargo, los cursos no lineales permiten a los estudiantes realizar las lecciones y evaluaciones en cualquier orden, lo que hace que la predicción del rendimiento sea más difícil debido a la variación de los porcentajes de evaluación acumulada entre los estudiantes en un momento dado. Esta tesis de máster tiene como objetivo desarrollar un método basado en datos para la predicción temprana del rendimiento de los estudiantes en cursos no lineales. Creamos un extractor de características y evaluamos tres tipos de características: compromiso, comportamiento y rendimiento. Los datos proceden de cursos de Moodle diseñados para preparar a estudiantes de secundaria para un examen de acceso a una universidad pública. Nuestro método logró predicciones tempranas al 20% de la evaluación del peso acumulado con una puntuación F1 de 0.73 para la clasificación binaria y un R² de 0.40 para la regresión. También llevamos a cabo un análisis de la importancia de las características, mostrando que las características de rendimiento y comportamiento son los predictores más significativos, con características de compromiso, como el tiempo dedicado a los recursos educativos, que también contribuyen significativamente. Además de predecir el rendimiento de los alumnos, realizamos un análisis de agrupación e identificamos cuatro patrones que aparecen de forma consistente en varias evaluaciones de peso acumulativo. Estos patrones influyen significativamente en el rendimiento y pueden ayudar a los educadores a proporcionar mejores comentarios y una atención más personalizada a los estudiantes.ModelamientoCOL0044448MaestríaMagíster en Ingeniería de Telecomunicaciones67 páginasapplication/pdfengUniversidad de AntioquiaMaestría en Ingeniería de TelecomunicacionesFacultad de IngenieríaCampus Medellín - Ciudad Universitariahttp://creativecommons.org/licenses/by-nc-sa/4.0/info:eu-repo/semantics/openAccessAttribution-NonCommercial-ShareAlike 4.0 Internationalhttp://purl.org/coar/access_right/c_abf2Machine learningAprendizaje automáticoData miningMOOCs (Web-based instruction)Cursos en línea masivos en abiertoStudent Performance Predictionhttp://id.loc.gov/authorities/subjects/sh85079324http://id.loc.gov/authorities/subjects/sh97002073http://id.loc.gov/authorities/subjects/sh2013002540Methodology for the analysis of student behavior and performance in an online courseMetodología para el análisis del comportamiento y el desempeño de los estudiantes en un curso en líneaTrabajo de grado - Maestríahttp://purl.org/redcol/resource_type/TMTexthttp://purl.org/coar/version/c_b1a7d7d4d402bcceinfo:eu-repo/semantics/masterThesisinfo:eu-repo/semantics/draft@article{ellis2009learning, title={Learning management systems}, author={Ellis, Ryann K}, journal={Alexandria, VI: American Society for Training \& Development (ASTD)}, year={2009} }@inproceedings{llamas2011useoflms, title={Use of LMS functionalities in engineering education}, author={Llamas, Mart{\\i}n and Caeiro, Manuel and Castro, Manuel and Plaza, Inmaculada and Tovar, Edmundo}, booktitle={2011 Frontiers in Education Conference (FIE)}, pages={S1G--1}, year={2011}, organization={IEEE} }@article{chen2014ahybrid, title={A hybrid recommendation algorithm adapted in e-learning environments}, author={Chen, Wei and Niu, Zhendong and Zhao, Xiangyu and Li, Yi}, journal={World Wide Web}, volume={17}, number={2}, pages={271--284}, year={2014}, publisher={Springer} }@article{seo2021analysis, title={Analysis of LMS Data of Distance Lifelong Learning Center Learners and Drop-out Prediction}, author={Seo, Jong-Taek and Park, Bok-Nyong and Kim, Young-gi and Yeon, Ko-Woon}, journal={Journal of Human-centric Science and Technology Innovation}, volume={1}, number={3}, pages={23--32}, year={2021} }@incollection{mobasher2007data, title={Data mining for web personalization}, author={Mobasher, Bamshad}, booktitle={The adaptive web}, pages={90--135}, year={2007}, publisher={Springer} }@article{conijn2016predicting, title={Predicting student performance from LMS data: A comparison of 17 blended courses using Moodle LMS}, author={Conijn, Rianne and Snijders, Chris and Kleingeld, Ad and Matzat, Uwe}, journal={IEEE Transactions on Learning Technologies}, volume={10}, number={1}, pages={17--29}, year={2016}, publisher={IEEE} }@article{hooshyar2019mining, title={Mining educational data to predict students’ performance through procrastination behavior}, author={Hooshyar, Danial and Pedaste, Margus and Yang, Yeongwook}, journal={Entropy}, volume={22}, number={1}, pages={12}, year={2019}, publisher={MDPI} }@article{tamada2022predicting, title={Predicting students at risk of dropout in technical course using LMS logs}, author={Tamada, Mariela Mizota and Giusti, Rafael and Netto, Jos{\e} Francisco de Magalh{\~a}es}, journal={Electronics}, volume={11}, number={3}, pages={468}, year={2022}, publisher={MDPI} }@article{cerezo2016students, title={Students LMS interaction patterns and their relationship with achievement: A case study in higher education}, author={Cerezo, Rebeca and S{\a}nchez-Santill{\a}n, Miguel and Paule-Ruiz, M Puerto and N{\u}{\~n}ez, J Carlos}, journal={Computers \& Education}, volume={96}, pages={42--54}, year={2016}, publisher={Elsevier} }@article{macfadyen2010mining, title={Mining LMS data to develop an “early warning system” for educators: A proof of concept}, author={Macfadyen, Leah P and Dawson, Shane}, journal={Computers \& education}, volume={54}, number={2}, pages={588--599}, year={2010}, publisher={Elsevier} }@article{tomasevic2020anoverview, title={An overview and comparison of supervised data mining techniques for student exam performance prediction}, author={Tomasevic, Nikola and Gvozdenovic, Nikola and Vranes, Sanja}, journal={Computers \& education}, volume={143}, pages={103676}, year={2020}, publisher={Elsevier} }@article{ljubobratovic2019using, title={Using LMS Activity Logs to Predict Student Failure with Random Forest Algorithm}, author={Ljubobratovi{\c}, Dejan and Mateti{\c}, Maja}, journal={The Future of Information Sciences}, pages={113}, year={2019} }@article{riestra2021massive, title={Massive LMS log data analysis for the early prediction of course-agnostic student performance}, author={Riestra-Gonz{\a}lez, Moises and del Puerto Paule-Ru{\\i}z, Maria and Ortin, Francisco}, journal={Computers \& Education}, volume={163}, pages={104108}, year={2021}, publisher={Elsevier} }@inproceedings{tamada2021predicting, title={Predicting student performance based on logs in moodle LMS}, author={Tamada, Mariela Mizota and Giusti, Rafael and de Magalh{\~a}es Netto, Jos{\e} Francisco}, booktitle={2021 IEEE Frontiers in Education Conference (FIE)}, pages={1--8}, year={2021}, organization={IEEE} }@article{lopez2020towards, title={Towards portability of models for predicting students’ final performance in university courses starting from moodle logs}, author={L{\o}pez-Zambrano, Javier and Lara, Juan A and Romero, Cristobal}, journal={Applied Sciences}, volume={10}, number={1}, pages={354}, year={2020}, publisher={MDPI} }@article{jokhan2019early, title={Early warning system as a predictor for student performance in higher education blended courses}, author={Jokhan, Anjeela and Sharma, Bibhya and Singh, Shaveen}, journal={Studies in Higher Education}, volume={44}, number={11}, pages={1900--1911}, year={2019}, publisher={Taylor \& Francis} }@misc{moodle2024, title = {Moodle Database schema}, howpublished = {\url{https://moodledev.io/docs/apis/core/dml/database-schema}}, note = {Accessed: 2024} }@article{romero2020educational, title={Educational data mining and learning analytics: An updated survey}, author={Romero, Cristobal and Ventura, Sebastian}, journal={Wiley interdisciplinary reviews: Data mining and knowledge discovery}, volume={10}, number={3}, pages={e1355}, year={2020}, publisher={Wiley Online Library} }@article{ray2018applications, title={Applications of educational data mining and learning analytics tools in handling big data in higher education}, author={Ray, Santosh and Saeed, Mohammed}, journal={Applications of Big Data analytics: Trends, issues, and challenges}, pages={135--160}, year={2018}, publisher={Springer} }@inproceedings{kloft2014predicting, title={Predicting MOOC dropout over weeks using machine learning methods}, author={Kloft, Marius and Stiehler, Felix and Zheng, Zhilin and Pinkwart, Niels}, booktitle={Proceedings of the EMNLP 2014 workshop on analysis of large scale social interaction in MOOCs}, pages={60--65}, year={2014} }@article{nordin2015tecnhology, title={Technology acceptance of massive open online courses in Malaysia.}, author={Nordin, Norazah and Norman, Helmi and Embi, Mohamad Amin}, journal={Malaysian Journal of Distance Education}, volume={17}, number={2}, year={2015} }@article{nabizadeh2020adaptive, title={Adaptive learning path recommender approach using auxiliary learning objects}, author={Nabizadeh, Amir Hossein and Goncalves, Daniel and Gama, Sandra and Jorge, Joaquim and Rafsanjani, Hamed N}, journal={Computers \& Education}, volume={147}, pages={103777}, year={2020}, publisher={Elsevier} }@article{alsadoon2020theimpact, title={The impact of an adaptive e-course on students’ achievements based on the students’ prior knowledge}, author={Alsadoon, Elham}, journal={Education and information technologies}, volume={25}, number={5}, pages={3541--3551}, year={2020}, publisher={Springer} }@article{chen2018recommendation, title={Recommendation system for adaptive learning}, author={Chen, Yunxiao and Li, Xiaoou and Liu, Jingchen and Ying, Zhiliang}, journal={Applied psychological measurement}, volume={42}, number={1}, pages={24--41}, year={2018}, publisher={Sage Publications Sage CA: Los Angeles, CA} }@inproceedings{mercado2023work, title={Work in progress: A didactic strategy based on Machine Learning for adaptive learning in virtual environments}, author={Mercado, Jhon and Mendoza, Carlos H and Ramirez-Salazar, Doris A and Valderrama, Angela and Gaviria-Gomez, Natalia and Botero, Juan F and Fletscher, Luis}, booktitle={2023 IEEE World Engineering Education Conference (EDUNINE)}, pages={1--4}, year={2023}, organization={IEEE} }@article{adnan2021predicting, title={Predicting at-risk students at different percentages of course length for early intervention using machine learning models}, author={Adnan, Muhammad and Habib, Asad and Ashraf, Jawad and Mussadiq, Shafaq and Raza, Arsalan Ali and Abid, Muhammad and Bashir, Maryam and Khan, Sana Ullah}, journal={Ieee Access}, volume={9}, pages={7519--7539}, year={2021}, publisher={IEEE} }@article{kuzilek2017open, title={Open university learning analytics dataset}, author={Kuzilek, Jakub and Hlosta, Martin and Zdrahal, Zdenek}, journal={Scientific data}, volume={4}, number={1}, pages={1--8}, year={2017}, publisher={Nature Publishing Group} }@article{cohausz2023investigating, title={Investigating the Importance of Demographic Features for EDM-Predictions.}, author={Cohausz, Lea and Tschalzev, Andrej and Bartelt, Christian and Stuckenschmidt, Heiner}, journal={International Educational Data Mining Society}, year={2023}, publisher={ERIC} }@article{hoq2023analysis, title={Analysis of an Explainable Student Performance Prediction Model in an Introductory Programming Course.}, author={Hoq, Muntasir and Brusilovsky, Peter and Akram, Bita}, journal={International Educational Data Mining Society}, year={2023}, publisher={ERIC} }@inproceedings{rohani2023early, title={Early prediction of student performance in a health data science MOOC}, author={Rohani, Narjes and Gal, Kobi and Gallagher, Michael and Manataki, Areti}, booktitle={Proceedings of the 16th International Conference on Educational Data Mining}, year={2023}, organization={International Educational Data Mining Society} }@inproceedings{mao2022cross, title={Cross-lingual adversarial domain adaptation for novice programming}, author={Mao, Ye and Khoshnevisan, Farzaneh and Price, Thomas and Barnes, Tiffany and Chi, Min}, booktitle={Proceedings of the AAAI Conference on Artificial Intelligence}, volume={36}, number={7}, pages={7682--7690}, year={2022} }@article{lundberg2017unified, title={A unified approach to interpreting model predictions}, author={Lundberg, Scott M and Lee, Su-In}, journal={Advances in neural information processing systems}, volume={30}, year={2017} }@article{cenka2022analysing, title={Analysing student behaviour in a learning management system using a process mining approach.}, author={Cenka, Baginda Anggun Nan and Santoso, Harry B and Junus, Kasiyah}, journal={Knowledge Management \& E-Learning}, volume={14}, number={1}, pages={62--80}, year={2022}, publisher={ERIC} }@article{bessadok2023exploring, title={Exploring students digital activities and performances through their activities logged in learning management system using educational data mining approach}, author={Bessadok, Adel and Abouzinadah, Ehab and Rabie, Osama}, journal={Interactive Technology and Smart Education}, volume={20}, number={1}, pages={58--72}, year={2023}, publisher={Emerald Publishing Limited} }@book{joshi2016ML, title={Python machine learning cookbook}, author={Joshi, Prateek}, year={2016}, publisher={Packt Publishing Ltd} }@article{cawley2010over, title={On over-fitting in model selection and subsequent selection bias in performance evaluation}, author={Cawley, Gavin C and Talbot, Nicola LC}, journal={The Journal of Machine Learning Research}, volume={11}, pages={2079--2107}, year={2010}, publisher={JMLR. org} }@article{Li2018Technology, title={Technology tools in distance education: A review of faculty adoption}, author={Li, Rui and Singh, JT and Bunk, Jennifer}, journal={EdMedia+ Innovate Learning}, pages={1982--1987}, year={2018}, publisher={Association for the Advancement of Computing in Education (AACE)} }@article{Hew2014Students, title={Students’ and instructors’ use of massive open online courses (MOOCs): Motivations and challenges}, author={Hew, Khe Foon and Cheung, Wing Sum}, journal={Educational research review}, volume={12}, pages={45--58}, year={2014}, publisher={Elsevier} }@inproceedings{morales2014telescope, title={Telescope, a MOOCs initiative in latin America: Infrastructure, best practices, completion and dropout analysis}, author={Morales, Miguel and Rizzardini, Rocael Hern{\a}ndez and G{\"u}tl, Christian}, booktitle={2014 IEEE Frontiers in Education Conference (FIE) Proceedings}, pages={1--7}, year={2014}, organization={IEEE} }@misc{udea_virtual_2024, author = {Ude@ Educación Virtual}, title = {Ude@ Educación Virtual}, howpublished = {\url{https://udearroba.udea.edu.co/home/}}, year = 2024, }@article{anderson2005search, title={The search for learning community in learner paced distance education: Or,Having your cake and eating it, too!}, author={Anderson, Terry and Annand, David and Wark, Norine}, journal={Australasian Journal of Educational Technology}, volume={21}, number={2}, year={2005} }@inproceedings{gao2021early, title={Early performance prediction using interpretable patterns in programming process data}, author={Gao, Ge and Marwan, Samiha and Price, Thomas W}, booktitle={Proceedings of the 52nd ACM technical symposium on computer science education}, pages={342--348}, year={2021} }@article{gamage2022systematic, title={A systematic review on trends in using Moodle for teaching and learning}, author={Gamage, Sithara HPW and Ayres, Jennifer R and Behrend, Monica B}, journal={International journal of STEM education}, volume={9}, number={1}, pages={9}, year={2022}, publisher={Springer} }@article{bradley2021learning, title={Learning Management System (LMS) use with online instruction.}, author={Bradley, Vaughn Malcolm}, journal={International Journal of Technology in Education}, volume={4}, number={1}, pages={68--92}, year={2021}, publisher={ERIC} }@article{badali2022role, title={The role of motivation in MOOCs’ retention rates: a systematic literature review}, author={Badali, Mehdi and Hatami, Javad and Banihashem, Seyyed Kazem and Rahimi, Ebrahim and Noroozi, Omid and Eslami, Zahra}, journal={Research and Practice in Technology Enhanced Learning}, volume={17}, number={1}, pages={5}, year={2022}, publisher={Springer} }@article{wang2023factors, title={Factors of dropout from MOOCs: a bibliometric review}, author={Wang, Wei and Zhao, Yongyong and Wu, Yenchun Jim and Goh, Mark}, journal={Library Hi Tech}, volume={41}, number={2}, pages={432--453}, year={2023}, publisher={Emerald Publishing Limited} }@article{polyzou2019feature, title={Feature extraction for next-term prediction of poor student performance}, author={Polyzou, Agoritsa and Karypis, George}, journal={IEEE Transactions on Learning Technologies}, volume={12}, number={2}, pages={237--248}, year={2019}, publisher={IEEE} }@article{ulitzsch2021combining, title={Combining clickstream analyses and graph-modeled data clustering for identifying common response processes}, author={Ulitzsch, Esther and He, Qiwei and Ulitzsch, Vincent and Molter, Hendrik and Nichterlein, Andr{\e} and Niedermeier, Rolf and Pohl, Steffi}, journal={psychometrika}, volume={86}, number={1}, pages={190--214}, year={2021}, publisher={Springer} }@online{moodleDatabaseSchema, author = "{Moodle Docs}", title = "{Database schema introduction}", year = "n.d.", url = "https://docs.moodle.org/dev/Database_schema_introduction", organization = "{Moodle Docs}", }@inproceedings{siemens2012learning, title={Learning analytics and educational data mining: towards communication and collaboration}, author={Siemens, George and Baker, Ryan SJ d}, booktitle={Proceedings of the 2nd international conference on learning analytics and knowledge}, pages={252--254}, year={2012} }@inproceedings{guo2014video, title={How video production affects student engagement: An empirical study of MOOC videos}, author={Guo, Philip J and Kim, Juho and Rubin, Rob}, booktitle={Proceedings of the first ACM conference on Learning scale conference}, pages={41--50}, year={2014} }@incollection{lecun2002efficient, title={Efficient backprop}, author={LeCun, Yann and Bottou, L{\e}on and Orr, Genevieve B and M{\"u}ller, Klaus-Robert}, booktitle={Neural networks: Tricks of the trade}, pages={9--50}, year={2002}, publisher={Springer} }@book{bishop2006pattern, title={Pattern recognition and machine learning}, author={Bishop, Christopher M and Nasrabadi, Nasser M}, volume={4}, number={4}, year={2006}, publisher={Springer} }@article{kim2017understanding, title={Understanding one-way ANOVA using conceptual figures}, author={Kim, Tae Kyun}, journal={Korean journal of anesthesiology}, volume={70}, number={1}, pages={22}, year={2017}, publisher={Korean Society of Anesthesiologists} }@article{scikit-learn, title={Scikit-learn: Machine Learning in {P}ython}, author={Pedregosa, F. and Varoquaux, G. and Gramfort, A. and Michel, V. and Thirion, B. and Grisel, O. and Blondel, M. and Prettenhofer, P. and Weiss, R. and Dubourg, V. and Vanderplas, J. and Passos, A. and Cournapeau, D. and Brucher, M. and Perrot, M. and Duchesnay, E.}, journal={Journal of Machine Learning Research}, volume={12}, pages={2825--2830}, year={2011} }@article{saarela2021comparison, title={Comparison of feature importance measures as explanations for classification models}, author={Saarela, Mirka and Jauhiainen, Susanne}, journal={SN Applied Sciences}, volume={3}, number={2}, pages={272}, year={2021}, publisher={Springer} }@inproceedings{trivedi2011clustering, title={Clustering students to generate an ensemble to improve standard test score predictions}, author={Trivedi, Shubhendu and Pardos, Zachary A and Heffernan, Neil T}, booktitle={Artificial Intelligence in Education: 15th International Conference, AIED 2011, Auckland, New Zealand, June 28--July 2011 15}, pages={377--384}, year={2011}, organization={Springer} }@article{alsariera2022assessment, title={Assessment and evaluation of different machine learning algorithms for predicting student performance}, author={Alsariera, Yazan A and Baashar, Yahia and Alkawsi, Gamal and Mustafa, Abdulsalam and Alkahtani, Ammar Ahmed and Ali, Norashikin}, journal={Computational Intelligence and Neuroscience}, volume={2022}, year={2022}, publisher={Hindawi Limited} }PublicationORIGINALMercadoJhon_2025_Student_Performance_Prediction.pdfMercadoJhon_2025_Student_Performance_Prediction.pdfTesis de maestríaapplication/pdf3036100https://bibliotecadigital.udea.edu.co/bitstreams/a74c600d-5002-4a62-a8f6-443099d6126a/download78e3bf52652ce39b0a9062aac086cf95MD52trueAnonymousREADCC-LICENSElicense_rdflicense_rdfapplication/rdf+xml; charset=utf-81160https://bibliotecadigital.udea.edu.co/bitstreams/e7e80f1b-1af4-4e8d-8ff6-44b982f6fc51/download5643bfd9bcf29d560eeec56d584edaa9MD53falseAnonymousREADLICENSElicense.txtlicense.txttext/plain; charset=utf-814837https://bibliotecadigital.udea.edu.co/bitstreams/f34f4e84-3064-4ce4-beef-6f23ef86e20e/downloadb76e7a76e24cf2f94b3ce0ae5ed275d0MD54falseAnonymousREADTEXTMercadoJhon_2025_Student_Performance_Prediction.pdf.txtMercadoJhon_2025_Student_Performance_Prediction.pdf.txtExtracted texttext/plain100763https://bibliotecadigital.udea.edu.co/bitstreams/7fd76184-b916-4477-8337-cc6a6e07db1a/download2d29f08a30ed5cd66bc2313df293efa2MD55falseAnonymousREADTHUMBNAILMercadoJhon_2025_Student_Performance_Prediction.pdf.jpgMercadoJhon_2025_Student_Performance_Prediction.pdf.jpgGenerated Thumbnailimage/jpeg6840https://bibliotecadigital.udea.edu.co/bitstreams/aeb8f047-74c7-4a28-8774-0be2b2919fd8/download96879fe5e4f8b698e8a41791b4c1e1bfMD56falseAnonymousREAD10495/46166oai:bibliotecadigital.udea.edu.co:10495/461662025-05-30 04:04:15.797http://creativecommons.org/licenses/by-nc-sa/4.0/Attribution-NonCommercial-ShareAlike 4.0 Internationalopen.accesshttps://bibliotecadigital.udea.edu.coRepositorio Institucional de la Universidad de Antioquiaaplicacionbibliotecadigitalbiblioteca@udea.edu.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 |