Detecting Media Bias in News Articles using Gaussian Bias Distributions
Detecting Media Bias in News Articles using Gaussian Bias Distributions
复制标题
使用高斯偏差分布检测新闻文章中的媒体偏差
DOI：
10.18653/v1/2020.findings-emnlp.383
复制
发表时间：
2020
期刊：
影响因子：
--
通讯作者：
Henning Wachsmuth
中科院分区：
文献类型：
--
作者：
Wei;Khalid Al Khatib;Benno Stein;Henning Wachsmuth
媒体在形成舆论方面起着重要作用。有偏见的媒体会影响人们走向不受欢迎的方向，因此应该揭露这种情况。我们观察到，基于特征和神经文本分类方法仅依赖于低水平词汇信息的分布，无法检测到媒体偏差。这一弱点在关于新事件的文章中尤为明显，因为这些文章中的词语出现在新的语境中，因此它们的“偏见预测性”不明确。因此，在本文中，我们研究了文章中关于有偏见陈述的二阶信息如何有助于提高检测效率。特别地，我们利用高斯混合模型中词汇级和信息级句子级偏差的频率、位置和顺序的概率分布。在现有的媒体偏见数据集上，我们发现偏见陈述的频率和位置强烈影响文章水平的偏见，而它们的确切顺序是次要的。使用句子级偏见检测的标准模型，我们提供了经验证据，表明使用二阶信息的文章级偏见检测器明显优于不使用二阶信息的文章级偏见检测器。
Media plays an important role in shaping public opinion. Biased media can influence people in undesirable directions and hence should be unmasked as such. We observe that feature-based and neural text classification approaches which rely only on the distribution of low-level lexical information fail to detect media bias. This weakness becomes most noticeable for articles on new events, where words appear in new contexts and hence their “bias predictiveness” is unclear. In this paper, we therefore study how second-order information about biased statements in an article helps to improve detection effectiveness. In particular, we utilize the probability distributions of the frequency, positions, and sequential order of lexical and informational sentence-level bias in a Gaussian Mixture Model. On an existing media bias dataset, we find that the frequency and positions of biased statements strongly impact article-level bias, whereas their exact sequential order is secondary. Using a standard model for sentence-level bias detection, we provide empirical evidence that article-level bias detectors that use second-order information clearly outperform those without.