This paper reports on progress in the development of a teaching module on machine learning with decision trees for secondary‐school students, in which students use survey data about media use to predict who plays online games frequently. This context is familiar to students and provides a link between school and everyday experience. In this module, they use CODAP's “Arbor” plug‐in to manually build decision trees and understand how to systematically build trees based on data. Further on, the students use a menu‐based environment in a Jupyter Notebook to apply an algorithm that automatically generates decision trees and to evaluate and optimize the performance of these. Students acquire technical and conceptual skills but also reflect on personal and social aspects of the uses of algorithms from machine learning.
This study examines modelling with machine learning. In the context of a yearlong data science course, the study explores how upper secondary students apply machine learning with Jupyter Notebooks and document the modelling process as a computational essay incorporating the different steps of the CRISP-DM cycle. The students’ work is based on a teaching module about decision trees in machine learning and a worked example of such a modelling process. The study outlines the students’ performance in carrying out the machine learning technically and reasoning about bias in the data, different data preparation steps, the application context, and the resulting decision model. Furthermore, the context of the study and the theoretical backgrounds are presented.
In the setting of design-based research, the second version of an experimental course on data science is implemented accompanied by research. The three modules of the course focus on “data and data detectives”, “machine learning” and a combination of both in working on a final project. In this paper, we will focus on the topic “decision trees” which is part of “machine learning”. The students learn approaches of how to build decision trees manually from data using the tree plugin of CODAP. Further on, they learn to design and code an algorithm with Python that automatically generates trees. Afterwards, the algorithm is applied to real data sets with the support of Jupyter Notebooks. The instructional approach provides a deep content knowledge, which also serves as a basis for discussing the difference between humans’ and machines’ building decision trees and the societal implications of implementing them in practice.
Decision-making processes are often based on data and data-driven machine learning methods in different areas such as recommender systems, medicine, criminalistics, etc. Well-informed citizens need at least a minimal understanding and critical reflection of corresponding data-driven machine learning methods. Decision trees are a method that can foster a preformal understanding of machine learning. We developed an exploratory teaching unit introducing decision trees in grade 6 along the question “How can Artificial Intelligence help us decide whether food is rather recommendable or not?” Students’ performances in an assessment task and self-assessment show that young learners can use a decision tree to classify new items and that they found the corresponding teaching unit informative.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.