Assessing Post-hoc Explainability of the BKT Algorithm

Assessing Post-hoc Explainability of the BKT Algorithm
复制标题

评估 BKT 算法的事后可解释性

DOI:
10.1145/3375627.3375856
复制
发表时间:
2020
期刊:
and Society
影响因子:
--
通讯作者:
Howley, Iris
Howley, Iris
中科院分区:
--
文献类型:
--
作者:
Zhou, Tongyu;Sheng, Haoyu;Howley, Iris

文献摘要

参考文献

被引文献

相似文献

随着机器智能越来越多地融入教育技术,教师和学生必须了解其系统所依赖的算法的潜在缺陷。本文介绍了设计和实施的交互式事后解释的贝叶斯知识追踪算法,在美国各地使用的学习分析系统中实现。经过以用户为中心的设计过程,以消除交互设计的困难,我们进行了一个对照实验,以评估是否互动或静态版本的可解释导致增加学习。我们的研究结果表明,通过解释学习算法取决于用户的教育背景。对于其他环境,事后可解释的设计者必须考虑用户的教育背景,以最好地确定如何通过人工智能增强系统进行更明智的决策。
As machine intelligence is increasingly incorporated into educational technologies, it becomes imperative for instructors and students to understand the potential flaws of the algorithms on which their systems rely. This paper describes the design and implementation of an interactive post-hoc explanation of the Bayesian Knowledge Tracing algorithm which is implemented in learning analytics systems used across the United States. After a user-centered design process to smooth out interaction design difficulties, we ran a controlled experiment to evaluate whether the interactive or static version of the explainable led to increased learning. Our results reveal that learning about an algorithm through an explainable depends on users' educational background. For other contexts, designers of post-hoc explainables must consider their users' educational background to best determine how to empower more informed decision-making with AI-enhanced systems.
OARS:探索在线学习的教师分析
DOI: --
发表时间: 2018
期刊: ACM Conference on Learning @ Scale
影响因子: --
作者:
J. Bassen;Iris K. Howley;Ethan Fast;John C. Mitchell;Candace Thille
通讯作者: Candace Thille
通过快速约会快速探索应用程序设计
DOI: --
发表时间: 2007
期刊: Ubiquitous Computing
影响因子: --
作者:
Scott Davidoff;Min Kyung Lee;A. Dey;J. Zimmerman
通讯作者: J. Zimmerman
DOI: 10.4324/9780203880869.ch43
发表时间: 2009
期刊: --
影响因子: --
作者:
David F. Feldon
通讯作者: David F. Feldon
DOI: --
发表时间: 1997-09
期刊: --
影响因子: --
作者:
I. Neath
通讯作者: I. Neath