Process-BERT: A Framework for Representation Learning on Educational Process Data
Process-BERT: A Framework for Representation Learning on Educational Process Data
复制标题
DOI：
10.48550/arxiv.2204.13607
复制
发表时间：
2022-04
期刊：
影响因子：
--
通讯作者：
Alexander Scarlatos;Christopher G. Brinton;Andrew S. Lan
中科院分区：
文献类型：
--
作者：
Alexander Scarlatos;Christopher G. Brinton;Andrew S. Lan
教育过程数据，即计算机化或在线学习平台中详细的学生活动日志，有可能为学生如何学习提供深入的见解。人们可以将过程数据用于许多下游任务，例如学习结果预测和自动提供个性化干预。然而，分析过程数据是具有挑战性的，因为过程数据的特定格式因不同的学习/测试场景而有很大不同。在本文中，我们提出了一个适用于多种不同学习场景的教育过程数据学习表示框架。我们的框架包括使用BERT类型目标从顺序过程数据中学习表示法的预训练步骤和进一步调整下游预测任务的表示法的微调步骤。我们将我们的框架应用于2019年全国成绩单数据挖掘竞赛数据集，该数据集由学生解题过程数据组成，并详细介绍了我们在此场景中使用的具体模型。我们进行了定量和定性的实验，以表明我们的框架产生的过程数据表示既具有预测性，又具有信息性。
Educational process data, i.e., logs of detailed student activities in computerized or online learning platforms, has the potential to offer deep insights into how students learn. One can use process data for many downstream tasks such as learning outcome prediction and automatically delivering personalized intervention. However, analyzing process data is challenging since the specific format of process data varies a lot depending on different learning/testing scenarios. In this paper, we propose a framework for learning representations of educational process data that is applicable across many different learning scenarios. Our framework consists of a pre-training step that uses BERT-type objectives to learn representations from sequential process data and a fine-tuning step that further adjusts these representations on downstream prediction tasks. We apply our framework to the 2019 nation's report card data mining competition dataset that consists of student problem-solving process data and detail the specific models we use in this scenario. We conduct both quantitative and qualitative experiments to show that our framework results in process data representations that are both predictive and informative.