Proposta de Melhoria dos Dados de Relatórios de uma Plataforma de MOOCS Brasileira

  • Vanessa Faria de Souza UFRGS - Universidade Federal do Rio Grande do Sul
  • Gabriela Trindade Perry UFRGS - Universidade Federal do Rio Grande do Sul
Palavras-chave: mineração de dados educacionais, análise de dados educacionais, ambientes virtuais de aprendizagem, cursos online massivos e abertos.

Resumo

A maior parte dos Ambientes Virtuais de Aprendizado (AVAs) não foi projetada para fazer registros de navegação com foco na mineração de dados, mas sim para informar professores e alunos sobre objetivos pedagógicos. Contudo, vem ganhando relevância o entendimento que as informações que podem ser extraídas dos registros de navegação podem ser bastante relevantes, o que motiva o vigoroso interesse na área de mineração de dados educacionais. Nesse sentido, neste artigo analisa-se como os dados coletados na plataforma Lúmina, AVA baseado em Moodle e que disponibiliza Massive Open Online Courses (MOOCs) da Universidade Federal do Rio Grande do Sul (UFRGS), podem ser melhorados, permitindo que mais informações sobre os estudantes sejam extraídas. Como modelo desta análise, usou-se o repositório DataShop do Pittsburgh Science of Learning Center (PSLC), que foi projetado a princípio para fornecer recursos educacionais online, e que tem apresentando bons resultados na aplicação de processos de mineração. O objetivo final é propor adequações à plataforma da UFRGS.

Referências

ALEVEN, V.; MCLAREN, B.; ROLL, I.; KOEDINGER, K. R. Toward Meta-Cognitive Tutoring: A Model of Help Seeking with a Cognitive Tutor. In: Int’ J. Artificial Intelligence and Education, vol. 16, no. 2, 2006, p. 101–128.
BAKER, R.; CORBETT, A.; KOEDINGER, K. R.; EVENSON, S.; ROLL, I.; WAGNER, A.; NAIM, M.; RASPAT, J.; BAKER, D.; BECK, J. Adapting to when students game an intelligent tutoring system. M. Ikeda, K. D. Ashley, T.-W. Chan (Eds.). In: 8th International Conference on Intelligent Tutoring Systems, 2006, p. 392-401.
BAKER, R.; ISOTANI, S.; CARVALHO, A. Mineração de dados educacionais: Oportunidades para o brasil. Brazilian Journal of Computers in Education, v.19, n. 02, p. 03-13, 2011.
BAKER, R. S. J. D.; CARVALHO, A. M. J. B.; RASPAT, J.; ALEVEN, V.; CORBETT, A. T.; KOEDINGER, K. R. Educational Software Features that Encourage and Discourage “Gaming the System”. In: 14th Int’ Conf. Artificial Intelligence in Education, 2009, p. 475–482.
BAKER, R. S. J. D.; CORBETT, A. T.; ALEVEN, V. More Accurate Student Modeling Through Contextual Estimation of Slip and Guess Probabilities in Bayesian Knowledge Tracing. In: 9th International Conference on Intelligent Tutoring Systems, 2008, p. 406-415.
BAKER, R. S. J. D.; GOWDA, S. M. An Analysis of the Differences in the Frequency of Students’ Disengagement in Urban, Rural, and Suburban High Schools. In: International Conference on Educational Data Mining, 3rd, Pittsburgh, PA, USA, 2010, p. 11-20.
BAKER, S.J.D.R.; YACEF, Y. The State of Educational Data Mining in 2009: A Review and Future Visions. JEDM – Journal of Educational Data Mining, 1(1), p. 3-17, 2009.
CEN, H.; KOEDINGER, K.; JUNKER, B. Learning Factors Analysis - A general method for cognitive model evaluation and improvement. In: 8th International Conference on Intelligent Tutoring Systems, 2006, p. 2-13.
CEN, H.; KOEDINGER, K.; JUNKER, B. A general method for cognitive model evaluation and improvement. Is over practice necessary? – Improving learning efficiency with the cognitive tutor through educational data mining. In: Rose Luckin and Ken Koedinger (Eds.) Proceedings of the 13th International Conferenceon Artificial Intelligence in Education, 2007 511-518.
CORBI, A.; BURGOS, D. Implementation of the Recommendation Model LIME in Cognitive and Visual Interactive Tutors from PSLC. IEEE Latin America Transactions, vol. 13, no. 2, p. 516-522, 2015.
GOWDA, S. M.; BAKER, R. S. J. D.; PARDOS, Z.; HEFFERNAN, N. T. The Sum is Greater Than the Parts: Ensembling Models of Student Knowledge in Educational Software. SIGKDD Explorations, vol. 13, no. 2, p. 37–44, 2011.
KOEDINGER, K. R.; STAMPER, J. C.; LEBER, B. SKOGSHOLM, A. Learn Lab’s Data Shop: A Data Repository and Analytics Tool Set for Cognitive Science. Topics in Cognitive Science, vol. 5, no. 3, p. 668–669, 2013.
KOEDINGER, K. R.; BAKER, R. S. J. D.; CUNNINGHAM, K.; SKOGSHOLM, A. LEBER, B.; STAMPER, J. A Data Repository for the EDM Community: The PSLC DataShop. Handbook of Educational Data Mining, CRC Press, p. 43–56, 2010.
KOEDINGER, K. R.; STAMPER, J. C. A Data Driven Approach to the Discovery of Better Cognitive Models. In: International Conference on Educational Data Mining, 3rd, Pittsburgh, PA, USA, 2010, p. 325-326.
KOEDINGER, K. R.; STAMPER, J. C.; MCLAUGHLIN, E. A. Tristan Nixon. Using Data-Driven Discovery of Better Student Models to Improve Student Learning. In: Conf. Artificial Intelligence in Education, 2013, p. 421–430.
KRÜGER, A.; MERCERON, A.; WOLF, B. A Data Model to Ease Analys is and Mining of Educational Data. In: International Conference on Educational Data Mining, (EDM), 3, p. 131-140, Pittsburgh, PA, USA, 2010.
LESZCZENSKI, J. M.; BECK J. E. What’s in a word? Extending learning factors analysis to model reading transfer. In: Educational Data Mining Workshop att he 14th International Conference on Artificial Intelligence in Education, Los Angeles, California, USA, 2007, p. 31-39.
MERCERON, A.; YACEF, K. Interestingness Measures for Association Rules in Educational Data. In: First International Conference on Educational Data Mining, 2008, p. 1-10
NWAIGWE, A.; KOEDINGER, K. R.; VANLEHN, K.; HAUSMANN, R.; WEINSTEIN, A. Exploring alternative methods for error attribution in learning curves analyses in inteligente tutoring systems. In: Luckin and Koedinger (Eds.) Proceedings of the 13th International Conference on Artificial Intelligence in Education, Los Angeles, California, USA, 2007, p. 246-253.
PERRY, G. T.; PADOVANI, H.; SOUZA, N. S.; ROSSATTO, P. What affects permanence in a MOOC about Chemistry? International Journal tor Innovation education and Research, v. 7, p. 19-29, 2019.
RAFFERTY, A. N.; YUDELSON, M. Applying learning factors analysis to build stereotypic student models. In: 13th International Conference on Artificial Intelligence in Education, Los Angeles, California, USA, 2007, p. 253-257.
RAFTERY, A. Bayesian Model Selection in Social Science Research. Sociological Methodology, v. 28, p. 111-163, 1995.
RAJNI, J.; MALAYA, D. B. An approach to generate students’ response on learning environment using Association Rule Mining. In: 2014 International Conference on Data Mining and Intelligent Computing (ICDMIC), New Delhi, India, 2014, p. 15-20
RITTER, S.; KOEDINGER, K. R. An architecture for plug-in tutor agents. Journal of Artificial Intelligence in Education, v.7, n. (3-4), p. 315-347, 1998.
ROMERO, C.; VENTURA, S. Educational Data Mining: A Survey from 1995 to 2005. Expert Systems with Applications, p. 125-146, 2007.
SOUZA, N. S.; SANTIAGO, G.; LIMA, J. V.; CANTO FILHO, A. B.; PERRY, G. T. Análise das Trajetórias de Aprendizagem de Estudantes Inscritos em um MOOC. Renote - Revista Novas Tecnologias na Educação, v. 16, n. 1, p. 1-11, 2018.
SOUZA, N. S.; WIVES, L. K.; PERRY, G. T. Tendências de Pesquisas que Utilizam Learning Analytics em MOOCs: um mapeamento sistemático. Renote - Revista Novas Tecnologias Na Educação, v. 17, n. 01, p. 82-92, 2019.
SOUZA, V. F.; PERRY, G. Identifying student behavior in MOOCs using Machine Learning. Jedm - International Journal for Innovation Education and Research, v. 7, p. 30-39, 2019.
SWEENEY, M.; RANGWALA, H.; LESTER, J. JOHRI, A. Next-Term Student Performance Prediction: A Recommender Systems Approach. Journal of Educational Data Mining. Memphis, Tennessee, p. 22-51, 2016.
Publicado
2020-08-04
Seção
Artigos Originais