Computing Reviews
Today's Issue Hot Topics Search Browse Recommended My Account Log In
Review Help
Data mining to increase teaching performance in engineering education
Pascal G., Tornillo J., Minnaard C., Comoglio M.  ICEIT 2019 (Proceedings of the 2019 8th International Conference on Educational and Information Technology, Cambridge, UK,  Mar 2-4, 2019) 308-311. 2019. Type: Proceedings
Date Reviewed: Oct 29 2020

A country’s success rate depends on many aspects. It is a mixture of different inner and outer conditions. Some factors are dependent on politics, and there is no possibility of building a strong and innovative industrial sector without an educated populace. Due to the complexity of many industrial processes, a constant inflow of engineers is highly desirable. But there can be no inflow of engineers without an appropriate teaching system in which performance is measured in different terms, that is, metrics and factors.

The authors focus on the engineering education system in Argentina. They propose three units of study (sets of knowledge): “basic sciences, basic technologies, and applied technologies of the engineering careers.” They apply principal component analysis (PCA) and establish five criteria to explain each one: “vertical articulation, retention strategies, teaching methodologies, evaluation methodologies, and learning methods and techniques.” Using Pentaho, “an open-source [database] with historical data from the years 2005-2017,” they study “the wisdom (set of knowledge) defined by the Federal Council of Deans of Engineering” and derive a set of indicators “from 12 metrics around student performance and behavior.”

Three key factors explain the basic sciences: vertical articulation, retention strategies, and teaching methodologies. For basic technologies, the above key factors “migrate slightly toward” not only retention strategies and teaching methodologies, but also an additional crucial factor: learning methods and techniques. Finally, an analysis of applied technologies confirms “the tendency toward the approach on the learning techniques”; evaluation methodologies are also important.

The paper shows how the use of data mining techniques can possibly improve teaching performance in engineering education. Keeping in mind that the authors look at a public education system, related issues include optimizing public resources and improving the quality and productivity of public universities.

Reviewer:  Dominik Strzalka Review #: CR147093 (2101-0013)
Bookmark and Share
  Editor Recommended
Featured Reviewer
General (G.0 )
Multivariate Statistics (G.3 ... )
Probability And Statistics (G.3 )
Would you recommend this review?
Other reviews under "General": Date
 On the foundations of computing
Primiero G.,  Oxford University Press, Oxford, UK, 2020. 320 pp. Type: Book (978-0-198835-65-3)
Aug 12 2021
Logical methods: the art of thinking abstractly and mathematically
Antonsen R.,  Springer, New York, NY, 2021. 304 pp. Type: Book (978-3-030637-76-7)
Jul 27 2021
randUTV: a blocked randomized algorithm for computing a rank-revealing UTV factorization
Martinsson P., Quintana-Ortí G., Heavner N.  ACM Transactions on Mathematical Software 45(1): 1-26, 2019. Type: Article
Jul 12 2021

E-Mail This Printer-Friendly
Send Your Comments
Contact Us
Reproduction in whole or in part without permission is prohibited.   Copyright © 2000-2022 ThinkLoud, Inc.
Terms of Use
| Privacy Policy