Scholarlink

Purpose <p>This study evaluates the effectiveness of a machine learning (ML) integrated science curriculum implemented within the Science Research Mentorship Program (SRMP) for high school youth at the American Museum of Natural History (AMNH) over 2&#xa0;years. The 4-week curriculum focused on ML knowledge gain, skill development, and self-efficacy, particularly for under-represented youth in STEM.</p> Background <p>ML is increasingly prevalent in STEM fields, making early exposure to ML methods and artificial intelligence (AI) literacy crucial for youth pursuing STEM careers. However, STEM fields, particularly those focused on AI research and development, suffer from a lack of diversity. Learning experiences that support the participation of under-represented groups in STEM and ML are essential to addressing this gap.</p> Results <p>Participant learning was assessed through pre- and post-surveys measuring ML knowledge, skills, and self-efficacy. Results from the implementation of the curriculum show that participants gained understanding of ML knowledge and skills (<i>p</i> &lt; 0.001, <i>d</i> = 1.083) and self-efficacy in learning ML concepts (<i>p</i> = 0.004, <i>d</i> = 0.676). On average, participants who identified as female and non-white showed greater learning gains than their white male peers (ML knowledge: <i>p</i> &lt; 0.001, <i>d</i> = 1.191; self-efficacy: <i>p</i> = 0.006, <i>d</i> = 0.631), decreasing gaps in ML knowledge, skills, and self-efficacy identified in pre-survey scores.</p> Conclusions <p>The ML-integrated curriculum effectively enhances students’ understanding and confidence in ML concepts, especially for under-represented groups in STEM, and provides a model for future ML education initiatives in informal science settings. We suggest that policy makers and school leaders take into account that high school age youth can learn ML concepts through integrated curricula while maintaining an awareness that curriculum effectiveness varies across demographic groups.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Study of an effective machine learning-integrated science curriculum for high school youth in an informal learning setting

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年4月19日

查看全文
  • Gabrielle Rabinowitz,
  • Katherine S. Moore,
  • Safinah Ali,
  • Mark Weckel,
  • Irene Lee,
  • Preeti Gupta,
  • Rachel Chaffee

摘要

Purpose

This study evaluates the effectiveness of a machine learning (ML) integrated science curriculum implemented within the Science Research Mentorship Program (SRMP) for high school youth at the American Museum of Natural History (AMNH) over 2 years. The 4-week curriculum focused on ML knowledge gain, skill development, and self-efficacy, particularly for under-represented youth in STEM.

Background

ML is increasingly prevalent in STEM fields, making early exposure to ML methods and artificial intelligence (AI) literacy crucial for youth pursuing STEM careers. However, STEM fields, particularly those focused on AI research and development, suffer from a lack of diversity. Learning experiences that support the participation of under-represented groups in STEM and ML are essential to addressing this gap.

Results

Participant learning was assessed through pre- and post-surveys measuring ML knowledge, skills, and self-efficacy. Results from the implementation of the curriculum show that participants gained understanding of ML knowledge and skills (p < 0.001, d = 1.083) and self-efficacy in learning ML concepts (p = 0.004, d = 0.676). On average, participants who identified as female and non-white showed greater learning gains than their white male peers (ML knowledge: p < 0.001, d = 1.191; self-efficacy: p = 0.006, d = 0.631), decreasing gaps in ML knowledge, skills, and self-efficacy identified in pre-survey scores.

Conclusions

The ML-integrated curriculum effectively enhances students’ understanding and confidence in ML concepts, especially for under-represented groups in STEM, and provides a model for future ML education initiatives in informal science settings. We suggest that policy makers and school leaders take into account that high school age youth can learn ML concepts through integrated curricula while maintaining an awareness that curriculum effectiveness varies across demographic groups.