Statistical Analyses of Learning Metrics in High School: a Study for Personalized Feedback Purposes

• Maely Moraes UFRR
• Gabriel Leitão IFAM
• Áurea Melo UEA
• Raimundo Barreto UFAM

DOI: https://doi.org/10.5753/sbie.2023.235145

Resumo

Improving the teaching-learning process depends on the availability of useful information for decision-making. However, considering the sizeable increase in data generated by educational platforms, performing statistical analyses which can support proper pedagogical choices for teachers and personalized guidance for students has become a real challenge. This paper is in this context, where the main goal is understanding the data and learning metrics and identifying important information about the studied sample to support personalized feedback in a timely manner, in addition to subsequent quantitative analysis. Thus, this article presents an exploratory analysis of interaction data on an educational platform while applying preparatory simulations for the entrance exam in high school classes. The methodology adopted consisted of organizing and tabulating the data, generating information from graphs, calculating statistics on the variables of interest, and interpreting them. The results indicated the most relevant metrics to predict the student's situation at the end of the course besides the Traditional Score (TS). In addition, feedback examples were proposed based on the identified scenarios from the outcomes of the statistical analysis and learning metrics that aim to expand the evaluative elements beyond right and wrong.

Referências

Baldassarre, M. (2016). Think big: learning contexts, algorithms and data science. Research on Education and Media, 8 (2), 69–83.

Costa, C. S. and Mattos, F. R. P. (2016). Tecnologia na sala de aula em relatos de professores. Curitiba: CRV, 202.

Cutumisu, M. and Schwartz, D. L. (2021). Feedback choices and their relations to learning are ageinvariant starting in middle school: A secondary data analysis. Computers & Education, 171, 104215.

Daniel, B. (2015). Big data and analytics in higher education: Opportunities and challenges. British journal of educational technology, 46(5), 904–920.

de Macêdo Santiago, L. B., Vasconcelos, K. C., and Santana, J. R. (2016). O uso dos artefatos tecnológicos virtuais e digitais na escola. ARTEFACTUM-Revista de estudos em Linguagens e Tecnologia, 13(2).

Detoni, D., Araujo, R. M., and Cechinel, C. (2014). Predição de reprovação de alunos de educação a distância utilizando contagem de interações. In Anais do Simpósio Brasileiro de Informática na Educação (Vol. 25, N. 1, p. 896).

Fávero, L. P. and Belfiore, P. (2017). Manual de análise de dados: estatística e modelagem multivariada com Excel®, SPSS® e Stata®. Elsevier Brasil.

Gonçalves, E. J. T., Vilela, J. F. F., and Bezerra, J. D. M. (2018). Análise estatística de notas e interações em cursos a distância. In Anais do Simpósio Brasileiro de Informática na Educação (Vol. 29, p. 71).

Govindarajan, K., Kumar, V. S., and Boulanger, D. (2015). Learning analytics solution for reducing learners’ course failure rate. In 2015 IEEE seventh international conference on technology for education (T4E) (pp. 83–90). IEEE.

Jones, Z. and Linder, F. (2015). Exploratory data analysis using random forests. In Prepared for the 73rd annual MPSA conference, 1–31.

Kassambara, A. (2017). Practical guide to principal component methods in R: PCA, M (CA), FAMD, MFA, HCPC, factoextra (Vol. 2). Sthda.

Koenka, A. C. and Anderman, E. M. (2019). Personalized feedback as a strategy for improving motivation and performance among middle school students. Middle School Journal, 50(5), 15–22.

Leitão, G. D. S. (2017). Uma plataforma de suporte ao docente no contexto da educação digital. M.S. thesis, Universidade Federal do Amazonas. Leitão, G. D. S. (2023). Um método baseado em objetos tangíveis para verificação da aprendizagem. PhD thesis, Universidade Federal do Amazonas.

Leitão, G., Colonna, J., Monteiro, E., Oliveira, E., and Barreto, R. (2020). New metrics for learning evaluation in digital education platforms. arXiv preprint arXiv:2006.14711.

Maier, U. and Klotz, C. (2022). Personalized feedback in digital learning environments: Classification framework and literature review. Computers and Education: Artificial Intelligence, 3, 100080.

Mandrekar, S. J. and Mandrekar, J. N. (2003). Are our data symmetric?. Statistical methods in medical research, 12(6), 505-513.

Martin, F. and Ndoye, A. (2016). Using learning analytics to assess student learning in online courses. Journal of University Teaching & Learning Practice, 13(3), 7.

Paiva, R., Bittencourt, I. I., and Lemos, W. (2019). Helping teachers visualize students’ performance. In Brazilian Symposium on Computers in Education (Simpósio Brasileiro de Informática na Educação-SBIE) (Vol. 30, N. 1, p. 1731).

Purwoningsih, T., Santoso, H. B., and Hasibuan, Z. A. (2020). Data analytics of students’ profiles and activities in a full online learning context. In 2020 Fifth International Conference on Informatics and Computing (ICIC) (pp. 1–8). IEEE.

Ramos, J. L. C., Rodrigues, R. L., Silva, J. C. S., and Gomes, A. S. (2014). Analisando fatores que afetam o desempenho de estudantes iniciantes em um curso a distância. In Brazilian Symposium on Computers in Education (Simpósio Brasileiro de Informática na Educação-SBIE) (Vol. 25, N. 1, p. 99).

Reino, L. R. A. C., Hernández-Domínguez, A., Júnior, O. D. G. F., Carvalho, V. D. H., Barros, P. A. M., and de Melo Braga, M. (2015). Análise das causas da evasão na educação a distância em uma instituição federal de ensino superior. In Brazilian Symposium on Computers in Education (Simpósio Brasileiro de Informática na Educação-SBIE) (Vol. 26, N. 1, p. 91).

Sousa, E. B. D., Alexandre, B., Ferreira Mello, R., Pontual Falcão, T., Vesin, B. and Gašević, D. (2021). Applications of learning analytics in high schools: A systematic literature review. Frontiers in Artificial Intelligence, 4, 737891.

Souza, T. I., Franco, A. O., Silva, T. E., and Vasconcelos, H. L. (2013). Avaliando o desempenho discente em um AVA: Um estudo de caso utilizando estatística multivariada. In Anais dos Workshops do Congresso Brasileiro de Informática na Educação (Vol. 2, N. 1, pp. 422–431).