用正交化方法减少模型对性别等敏感特征的依赖，提升在线学习参与度评估的公平性。
Automatic Assessment of Students' Classroom Engagement with Bias Mitigated Multi-task Model
- 采用属性正交正则化，让模型不依赖性别等敏感特征进行判断。
- 在敏感群体预测分布差异上，皮尔逊相关系数从0.897降至0.999，显著降低偏差。
- 适合教育技术、公平性算法研究者参考，尤其关注模型伦理与可解释性。
随着在线与虚拟学习的兴起，监测并提升学生参与度已成为有效教育的重要环节。传统评估方法难以直接应用于虚拟环境。本研究聚焦此问题，提出一种自动化系统以检测在线学习中的学生参与水平。我们设计了一种新型训练方法，能有效阻止模型利用性别等敏感特征进行预测，不仅有助于遵守伦理规范，还提升了模型预测的可解释性。通过在分模型分类器中引入属性正交正则化，并结合多种迁移学习策略，成功将未缓解模型在敏感群体间预测分布差异的皮尔逊相关系数从0.897降低至0.999，显著减少偏差。项目源码已公开于 https://github.com/ashiskb/elearning-engagement-study。
原文摘要 · Abstract (English)
With the rise of online and virtual learning, monitoring and enhancing student engagement have become an important aspect of effective education. Traditional methods of assessing a student's involvement might not be applicable directly to virtual environments. In this study, we focused on this problem and addressed the need to develop an automated system to detect student engagement levels during online learning. We proposed a novel training method which can discourage a model from leveraging sensitive features like gender for its predictions. The proposed method offers benefits not only in the enforcement of ethical standards, but also to enhance interpretability of the model predictions. We applied an attribute-orthogonal regularization technique to a split-model classifier, which uses multiple transfer learning strategies to achieve effective results in reducing disparity in the distribution of prediction for sensitivity groups from a Pearson correlation coefficient of 0.897 for the unmitigated model, to 0.999 for the mitigated model. The source code for this project is available on https://github.com/ashiskb/elearning-engagement-study .
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。