arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2010.04430cs.LGcs.HCcs.SIstat.ML
收藏

大规模随机实验揭示机器学习帮助人们更有效地学习和记忆

Large-scale randomized experiment reveals machine learning helps people learn and remember more effectively

Max Planck Institute for Software Systems(马克斯·普朗克软件系统研究所);Swift Management AG(Swift管理股份公司)

Utkarsh Upadhyay, Graham Lancashire, Christoph Moser, Manuel Gomez-Rodriguez

摘要:

机器学习通常专注于开发模型和算法,这些模型和算法最终将在需要智能的任务中取代人类。在这项工作中,我们不是取代人类,而是专注于揭示机器学习的潜力,以改善人们学习和记忆事实材料的方式。为此,我们进行了一项大规模的随机对照试验,数千名学习者来自移动领域的一个流行的学习应用程序。在控制学习的长度和频率后,我们发现使用机器学习优化学习会话的学习者比使用两种替代算法生成学习会话的学习者记住的内容长$\sim$ 67%。我们的随机对照试验还显示,使用机器学习优化学习课程的学习者在4-7天内返回应用程序的可能性增加了$\sim$ 50%。

英文摘要:

Machine learning has typically focused on developing models and algorithms that would ultimately replace humans at tasks where intelligence is required. In this work, rather than replacing humans, we focus on unveiling the potential of machine learning to improve how people learn and remember factual material. To this end, we perform a large-scale randomized controlled trial with thousands of learners from a popular learning app in the area of mobility. After controlling for the length and frequency of study, we find that learners whose study sessions are optimized using machine learning remember the content over $\sim$67% longer than those whose study sessions are generated using two alternative heuristics. Our randomized controlled trial also reveals that the learners whose study sessions are optimized using machine learning are $\sim$50% more likely to return to the app within 4-7 days.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑