Comparativo entre modelos de knowledge tracing aplicados a los ejercicios de la plataforma SENECODE

dc.contributorManrique Piramanrique, Rubén Francisco
dc.contributorAguirre Herrera, Sandra Leonor
dc.contributorMariño Drews, Olga
dc.creatorBravo Mora, Cristian Alejandro
dc.date.accessioned2023-06-23T14:24:21Z
dc.date.accessioned2023-09-07T00:17:57Z
dc.date.available2023-06-23T14:24:21Z
dc.date.available2023-09-07T00:17:57Z
dc.date.created2023-06-23T14:24:21Z
dc.date.issued2023-05-31
dc.identifierhttp://hdl.handle.net/1992/67849
dc.identifierinstname:Universidad de los Andes
dc.identifierreponame:Repositorio Institucional Séneca
dc.identifierrepourl:https://repositorio.uniandes.edu.co/
dc.identifier.urihttps://repositorioslatinoamericanos.uchile.cl/handle/2250/8727278
dc.description.abstractKnowledge Tracing (KT) es un área de investigación en la inteligencia artificial cuyo objetivo es modelar el conocimiento de un estudiante a través del análisis de sus interacciones en el tiempo durante su participación en un curso académico. En este trabajo se propone realizar un comparativo de diferentes modelos de KT, encontrados en la literatura del estado del arte, entrenados y evaluados con los ejercicios que los estudiantes del curso Introducción a la Programación suben a la plataforma conocida como SENECODE. Dicha plataforma recopila y califica el código fuente de los ejercicios de programación resueltos por estudiantes novatos de la Universidad de Los Andes. Seleccionando y aplicando varios modelos de KT a los datos de esta plataforma, se propone construir un modelo KT con variaciones en los datos de entrada, teniendo principalmente en cuenta el código fuente de los ejercicios realizados por los estudiantes junto a los datos tradicionales de KT para medir y predecir el nivel de maestría y conocimiento que cada estudiante tiene sobre los diferentes módulos del curso. Finalmente, se realiza una prueba de concepto para utilizar el modelo de KT para dar retroalimentación a los estudiantes en aquellos temas o módulos en el que posiblemente requieran un refuerzo.
dc.languagespa
dc.publisherUniversidad de los Andes
dc.publisherMaestría en Ingeniería de Sistemas y Computación
dc.publisherFacultad de Ingeniería
dc.publisherDepartamento de Ingeniería Sistemas y Computación
dc.relationAbdelrahman, G., y Wang, Q. (2019). Knowledge Tracing with Sequential Key-Value Memory Networks. En Proceedings of the 42nd international acm sigir conference on research and development in information retrieval. Washington: ACM Conference.
dc.relationAbdelrahman, G., Wang, Q., y Nunes, B. P. (2022). Knowledge Tracing: A Survey. ACM Computing Surveys(October). Descargado de http://arxiv.org/abs/2201.06953 doi: 10.1145/3569576
dc.relationAlbert T Corbett and John R Anderson. (1994). Knowledge tracing: Modeling the acquisition of procedural knowledge. UMUAI, 4, 253-278
dc.relationBadrinath, A., Wang, F., y Pardos, Z. (2021). pybkt: An accessible python library of bayesian knowledge tracing models. En Proceedings of the 14th international conference on educational data mining (pp. 468-474)
dc.relationbigdata ustc. (2021). Eduktm. https://github.com/bigdata-ustc/EduKTM. GitHub.
dc.relationBodily, R., Ikahihifo, T. K., Mackley, B., y Graham, C. R. (2018). The design, development, and implementation of student-facing learning analytics dashboards. Journal of Compu ting in Higher Education, 30(3), 572-598. Descargado de https://doi.org/10.1007/ s12528-018-9186-0 doi: 10.1007/s12528-018-9186-0
dc.relationCen, H., Koedinger, K., y Junker, B. (2006). Learning Factors Analysis - A General Method for Cognitive Model Evaluation and Improvement Learning Factors Analysis. ITS, 4053. doi: 10.1007/11774303
dc.relationChoi, Y., Lee, Y., Cho, J., Baek, J., Kim, B., Cha, Y., . . . Berkeley, U. C. (2020). Towards an Appropriate Query , Key , and Value Computation for Knowledge Tracing. En Proceedings of the seventh acm conference on learning. L@S.
dc.relationCORBET, A. T., y ANDERSON, J. R. (1995). Knowledge Tracing : Modeling the Acquisition of Procedural Knowledge. Kluwer Academic Publishers, 253-278
dc.relationDai, M., Hung, J.-l., Du, X., Tang, H., y Li, H. (2021). Knowledge Tracing : A Review of Available Technologies. Journal of E Journal of Educational T ducational Technology De echnology Development and Ex elopment and Exchange (JETDE), 14(2). doi: 10.18785/jetde.1402.01
dc.relationDiana, N., Grover, S., Eagle, M., Bienkowski, M., Stamper, J., y Basu, S. (2017). An instruc tor dashboard for real-time analytics in interactive programming assignments. ACM International Conference Proceeding Series, 272-279. doi: 10.1145/3027385.3027441
dc.relationDing, X., Han, T., Fang, Y., y Larson, E. (2022, aug). An approach for combining multimodal fusion and neural architecture search applied to knowledge tracing. Applied Intelligence. doi: 10.1007/s10489-022-04095-x
dc.relationGoodfellow, I., Bengio, Y., y Courville, A. (2016). Deep learning. MIT Press
dc.relationHwang, J. (2021). Juno dkt. https://github.com/juno-hwang/juno-dkt. GitHub.
dc.relationjdxyw. (2021). deepkt. https://github.com/jdxyw/deepKT. GitHub.
dc.relationJr, P., Analysis, P. F., Alternative, N., Tracing, K., Dimitrova, V., Conference, I., y Intelligence, A. (2009). Performance Factors Analysis - A New Alternative to Knowledge Tracing. AIED, 200, 531-538
dc.relationKlingler, S., Schwing, A. G., y Gross, M. (2017). Dynamic Bayesian Networks for Student. IEEE Trans. Learn. Technol. 10, 450´s462.
dc.relationLang, C. (2017). Opportunities for personalization in modeling students as Bayesian learners. ACM International Conference Proceeding Series(1), 41-45. doi: 10.1145/ 3027385.3027410
dc.relationLiang, Y., Peng, T., Pu, Y., y Wu, W. (2022). OPEN HELP - DKT : an interpretable cognitive model of how students learn programming based on deep knowledge tracing. Scientific Reports(0123456789), 1-11. Descargado de https://doi.org/10.1038/s41598-022 -07956-0 doi: 10.1038/s41598-022-07956-0
dc.relationLiu, Q., Shen, S., Huang, Z., Chen, E., Member, S., y Zheng, Y. (2021). A Survey of Knowledge Tracing. Cornell University. Descargado de https://arxiv.org/abs/2105.15106
dc.relationLiu, T. (2022). Knowledge tracing : A bibliometric analysis. Computers and Education: Artificial Intelligence, 3(July), 100090. Descargado de https://doi.org/10.1016/ j.caeai.2022.100090 doi: 10.1016/j.caeai.2022.100090
dc.relationLiu, Z., Liu, Q., Chen, J., Huang, S., Tang, J., y Luo, W. (2022). pykt: A python library to benchmark deep learning based knowledge tracing models. En Thirty-sixth conference on neural information processing systems datasets and benchmarks track.
dc.relationMay, R. M. (1976). Simple mathematical models with very complicated dynamics. Nature, 261(5560), 459-467.
dc.relationNagatani, K., Chen, Y.-y., y Chen, F. (2019). Augmenting Knowledge Tracing by Considering For getting Behavior. New York: The World Wide Web Conference (WWW 19). Association for Computing Machinery. doi: https://doi.org/10.1145/3308558.3313565
dc.relationNakagawa, H., Iwasawa, Y., y Matsuo, Y. (2019). Graph-based Knowledge Tracing: Mode ling Student Proficiency Using Graph Neural Network. En Eee/wic/acm international conference (pp. 156-163). Web Intelligence (WI)
dc.relationNoh, H. (2022). Knowledge tracing collection with pytorch. https://github.com/hcnoh/ knowledge-tracing-collection-pytorch. GitHub.
dc.relationOrr, J. W., y Russell, N. (2021). Automatic Assessment of the Design Quality of Python Programs with Personalized Feedback. Descargado de http://arxiv.org/abs/2106.01399
dc.relationPaaßen, B., McBroom, J., Jeffries, B., Yacef, K., y Koprinska, I. (2021). Mapping Python Programs to Vectors using Recursive Neural Encodings. Journal of Educational Data Mining, 13(3), 1-35. doi: 10.5281/zenodo.5634224
dc.relationPandey, S., y Karypis, G. (2019). A Self-Attentive model for Knowledge Tracing. EDM.
dc.relationPiech, C., Bassen, J., Huang, J., Ganguli, S., Sahami, M., Guibas, L., y Sohl-Dickstein, J. (2015). Deep knowledge tracing. En Advances in neural information processing systems (Vol. 2015-Janua, pp. 505-513).
dc.relationRegularization, P.-c., y Yeung, C.-k. (2018). Addressing two problems in deep knowledge tracing via prediction-consistent regularization. En Proceedings of the fifth annual acm conference on learning at scale (pp. 1-10). New York. doi: https://doi.org/10.1145/ 3231644.3231647
dc.relationShen, S., Liu, Q., Chen, E., Huang, Z., Huang, W., Yin, Y., . . . Wang, S. (2021). Learning Process consistent Knowledge Tracing. En Proceedings of the 27th acm sigkdd conference (pp. 1452-1460). Knowledge Discovery Data Mining.
dc.relationShi, Y., Chi, M., Barnes, T., y Price, T. (2022). Code-dkt: A code-based knowledge tracing model for programming tasks
dc.relationSmith, J. D., y Johnson, A. B. (2018). Bayesian modeling: Principles and applications. Journal of Statistical Methods, 45(2), 123-145
dc.relationWang, C., Sahebi, S., Zhao, S., Brusilovsky, P., y Moraes, L. O. (2021). Knowledge tracing for complex problem solving: Granular rank-based tensor factorization. UMAP 2021 - Pro ceedings of the 29th ACM Conference on User Modeling, Adaptation and Personalization, 179-188. doi: 10.1145/3450613.3456831
dc.relationXiao, Y., Xiao, R., Huang, N., Hu, Y., Li, H., y Sun, B. (2022, oct). Knowledge tracing based on multi-feature fusion. Neural Computing and Applications. Descargado de https:// link.springer.com/10.1007/s00521-022-07834-w doi: 10.1007/s00521-022-07834 -w
dc.relationZhang, J., Shi, X., King, I., y Yeung, D.-y. (2017). Dynamic Key-Value Memory Networks for Knowledge Tracing.
dc.relationZhu, M., Han, S., Yuan, P., y Lu, X. (2022). Enhancing Programming Knowledge Tracing by Interacting Programming Skills and Student Code. ACM International Conference Proceeding Series, 438-443. doi: 10.1145/3506860.3506870
dc.rightsAttribution-NonCommercial-NoDerivatives 4.0 Internacional
dc.rightsAttribution-NonCommercial-NoDerivatives 4.0 Internacional
dc.rightshttp://creativecommons.org/licenses/by-nc-nd/4.0/
dc.rightsinfo:eu-repo/semantics/openAccess
dc.rightshttp://purl.org/coar/access_right/c_abf2
dc.titleComparativo entre modelos de knowledge tracing aplicados a los ejercicios de la plataforma SENECODE
dc.typeTrabajo de grado - Maestría


Este ítem pertenece a la siguiente institución