arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2104.10130cs.CLcs.AI
收藏

不可靠新闻检测数据中的隐藏偏差

Hidden Biases in Unreliable News Detection Datasets

UNC Chapel Hill(北卡罗来纳大学教堂山分校);Amazon(亚马逊)

Xiang Zhou, Heba Elfardy, Christos Christodoulopoulos, Thomas Butler, Mohit Bansal

摘要:

自动不可靠新闻检测是一个具有重要意义的研究课题。最近,几篇论文在大规模新闻数据集上显示了有希望的结果,这些模型只使用文章本身,而不诉诸任何事实检查机制或检索任何支持证据。在这项工作中,我们将仔细研究这些数据集。虽然它们都为未来的研究提供了宝贵的资源,但我们观察到一些问题,这些问题可能导致在更现实的环境中无法推广的结果。具体来说,我们表明,选择偏差在数据汇集导致不希望的文物的数据集。此外,虽然大多数系统在单个文章的水平上进行训练和预测,但是训练和评估数据中的重叠文章源可以提供模型可以利用的强混杂因素。在存在这种混杂因素的情况下,模型可以通过直接记忆站点标签映射而不是对不可靠新闻检测的实际任务建模来实现良好的性能。我们观察到,在没有训练/测试源重叠的干净分离中测试的所有模型的准确度显著下降(>10%)。使用观察和实验结果,我们提供了实用的建议,如何创建更可靠的数据集不可靠的新闻检测任务。我们建议未来的数据集创建包括一个简单的模型作为难度/偏差探针,未来的模型开发使用一个干净的非重叠的网站和日期分割。

英文摘要:

Automatic unreliable news detection is a research problem with great potential impact. Recently, several papers have shown promising results on large-scale news datasets with models that only use the article itself without resorting to any fact-checking mechanism or retrieving any supporting evidence. In this work, we take a closer look at these datasets. While they all provide valuable resources for future research, we observe a number of problems that may lead to results that do not generalize in more realistic settings. Specifically, we show that selection bias during data collection leads to undesired artifacts in the datasets. In addition, while most systems train and predict at the level of individual articles, overlapping article sources in the training and evaluation data can provide a strong confounding factor that models can exploit. In the presence of this confounding factor, the models can achieve good performance by directly memorizing the site-label mapping instead of modeling the real task of unreliable news detection. We observed a significant drop (>10%) in accuracy for all models tested in a clean split with no train/test source overlap. Using the observations and experimental results, we provide practical suggestions on how to create more reliable datasets for the unreliable news detection task. We suggest future dataset creation include a simple model as a difficulty/bias probe and future model development use a clean non-overlapping site and date split.

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。

↑