A systematic review of teaching and learning machine learning in K-12 education

Abstract

The increasing attention to Machine Learning (ML) in K-12 levels and studies exploring a different aspect of research on K-12 ML has necessitated the need to synthesize this existing research. This study systematically reviewed how research on ML teaching and learning in K-12 has fared, including the current area of focus, and the gaps that need to be addressed in the literature in future studies. We reviewed 43 conference and journal articles to analyze specific focus areas of ML learning and teaching in K-12 from four perspectives as derived from the data: curriculum development, technology development, pedagogical development, and teacher training/professional development. The findings of our study reveal that (a) additional ML resources are needed for kindergarten to middle school and informal settings, (b) further studies need to be conducted on how ML can be integrated into subject domains other than computing, (c) most of the studies focus on pedagogical development with a dearth of teacher professional development programs, and (d) more evidence of societal and ethical implications of ML should be considered in future research. While this study recognizes the present gaps and direction for future research, these findings provide insight for educators, practitioners, instructional designers, and researchers into K-12 ML research trends to advance the quality of the emerging field.

AI literacy in K-12: a systematic literature review

“…These components included target audience, setting, duration, contents, pedagogical approaches to teaching, and assessment methods. Sanusi et al (2022) reviewed research on teaching machine learning in K-12 from four perspectives: curriculum development, technology development, pedagogical development, and teacher training development. The findings of the study revealed that more studies are needed on how to integrate machine learning into subjects other than computer science.…”

Not Just Training, Also Testing: High School Youths' Perspective-Taking through Peer Testing Machine Learning-Powered Applications

“…ML provides rich opportunities for K-12 youths to experiment with training data and learning algorithms. Yet, while there are numerous studies that have investigated youths' understanding of machine learning, most have done so from the perspective of having them train models [27], only few studies (e.g., [8,36,38]) have examined what youths can learn by also testing the models they trained. Furthermore, these studies highlight the need for providing scaffolds to support youths in testing their ML models.…”

“…However, in K-12 computing education most efforts have centered on having youths train models with less attention given to testing. For instance, recent systematic reviews rarely mention studies that discuss testing in teaching, learning, and assessing ML in K-12 contexts [9,21,25,27]. This is not only an issue in K-12 education but also in undergraduate ML education where testing is not always included as a necessary step for learners to consider in the ML pipeline [11,28].…”

Career Interest Assessment: College Students Career Planning Based On Machine Leaning

“…College students' career planning based on career interest assessment involves a structured approach to exploring potential career paths aligned with their skills, interests, and aspirations [8]. Utilizing career interest assessments, students gain valuable insights into their strengths, preferences, and values, which serve as a foundation for making informed decisions about their future.…”