A Proposal for Performance-based Assessment of the Learning of Machine Learning Concepts and Practices in K-12

• Published in: Informatics in education Vol. 21; no. 3; pp. 479 - 500
• Main Authors: Gresse von Wangenheim, Christiane, Da Cruz Alves, Nathalia, Rauber, Marcelo Fernando, Hauck, Jean Carlo Rossa, YETER, Ibrahim H
• Format: Journal Article
• Language: English
• Published: Vilnius Vilniaus Universiteto Leidykla 2022; Vilnius University Press; Institute of Mathematics and Informatics; Vilnius University Institute of Mathematics and Informatics, Lithuanian Academy of Sciences; Vilnius University
• Subjects: Active Learning; Algorithms; Artificial Intelligence; Artificial neural networks; assessment; Basic Skills; Classification; Computer Science; Computer Science Education; Concept Formation; Education; Educational Assessment; Educational evaluation; Educational Objectives; Elementary Secondary Education; Feedback; High School Students; Higher Education; ICT Information and Communications Technologies; Image classification; Influence of Technology; Information Science; Intelligent Tutoring Systems; Interrater Reliability; K-12; Kindergarten; Learning Processes; Machine learning; Measurement Techniques; Middle School Students; Networks; Object recognition; Performance Based Assessment; Research Reports; Rubric; Scoring Rubrics; Student Empowerment; Student Evaluation; Students; Teaching Methods; Units of Study; assessment; rubric; education; machine learning; K12
• ISSN: 1648-5831; 2335-8971
• DOI: 10.15388/infedu.2022.18

Although Machine Learning (ML) is used already in our daily lives, few are familiar with the technology. This poses new challenges for students to understand ML, its potential, and limitations as well as to empower them to become creators of intelligent solutions. To effectively guide the learning of ML, this article proposes a scoring rubric for the performance-based assessment of the learning of concepts and practices regarding image classification with artificial neural networks in K-12. The assessment is based on the examination of student-created artifacts as a part of open-ended applications on the use stage of the Use-Modify-Create cycle. An initial evaluation of the scoring rubric through an expert panel demonstrates its internal consistency as well as its correctness and relevance. Providing a first step for the assessment of concepts on image recognition, the results may support the progress of learning ML by providing feedback to students and teachers.