Artificial intelligence (AI) has rapidly pervaded and reshaped almost all walks of life, but efforts to promote AI literacy in K-12 schools remain limited. There is a knowledge gap in how to prepare teachers to teach AI literacy in inclusive classrooms and how teacher-led classroom implementations can impact students. This paper reports a comparison study to investigate the effectiveness of an AI literacy curriculum when taught by classroom teachers. The experimental group included 89 middle school students who learned an AI literacy curriculum during regular school hours. The comparison group consisted of 69 students who did not learn the curriculum. Both groups completed the same pre and post-test. The results show that students in the experimental group developed a deeper understanding of AI concepts and more positive attitudes toward AI and its impact on future careers after the curriculum than those in the comparison group. This shows that the teacher-led classroom implementation successfully equipped students with a conceptual understanding of AI. Students achieved significant gains in recognizing how AI is relevant to their lives and felt empowered to thrive in the age of AI. Overall this study confirms the potential of preparing K-12 classroom teachers to offer AI education in classrooms in order to reach learners of diverse backgrounds and broaden participation in AI literacy education among young learners.
1 July 2019 in British Journal of Educational Technology
Computer modeling promotes mechanistic reasoning when learners build and analyze models of complex systems to explore causal mechanisms and use models to generate patterns. StarLogo Nova (SLN), an agent‐based modeling (ABM) environment, enables novice programmers to model a system's individual components and investigate its emergent, collective behavior. Through case analysis of teachers using SLN, we demonstrate how ABM advances thinking about mechanisms generating phenomenon. Teachers who used simulation combined with the decoding of SLN models utilized mechanistic reasoning to make sense of how and why complex phenomenon emerged. Practitioner Notes: What is already known about this topic Mechanisms, or causal explanatory processes, are critical in science. Mechanistic reasoning is concerned with why a phenomenon occurs. Traditionally in science classrooms, teachers incorporate pre‐packaged simulations that limit the ability to understand mechanisms within the simulations. Agent‐based modeling empowers learners to model at the micro‐level to understand how macro‐level phenomenon emerge in complex systems. What this paper adds StarLogo Nova, an agent‐based modeling environment, has features that support mechanistic reasoning. Using simulation combined with decoding of models in StarLogo Nova promotes mechanistic explanations of why phenomenon occurs. Teachers are able to scaffold student interactions in StarLogo Nova to support students' mechanistic reasoning. Implications for practice and/or policy When using computer simulations in instruction, incorporate decoding of models to engage students in uncovering why a phenomenon occurs. In professional development programs on scientific modeling, it is important for educators to learn how decoding contributes to students' understanding of mechanisms in models and experience modeling as a scientific practice.