FrameAxis: characterizing microframe bias and intensity with word embedding.

FrameAxis: characterizing microframe bias and intensity with word embedding.
复制标题

DOI:
10.7717/peerj-cs.644
复制
发表时间:
2021
期刊:
PeerJ. Computer science
影响因子:
--
通讯作者:
Ahn YY
Ahn YY
中科院分区:
其他
文献类型:
--
作者:
Kwak H;An J;Jing E;Ahn YY

文献摘要

参考文献

被引文献

相似文献

框架是一个过程,强调一个问题的某一方面,而不是其他方面,推动读者或听众在这个问题上的不同立场,即使没有偏见的论点。在这里,我们提出FrameAxis,这是一种通过使用词嵌入识别文本中过度表示的最相关的语义轴(“微帧”)来表征文档的方法。我们的无监督方法可以很容易地应用于大型数据集,因为它不需要手动注释。它还可以通过考虑一组丰富的语义轴来提供细致入微的见解。FrameAxis旨在定量地梳理出文本中如何使用微帧的两个重要维度。微帧偏差捕获文本在特定微帧上的偏差程度,微帧强度显示特定微帧的使用程度。它们共同提供了文本的详细特征。我们通过将FrameAxis应用于从餐馆评论到政治新闻的多个数据集,证明了具有最高偏差和强度的微帧与情绪、话题和党派光谱很好地一致。现有的领域知识可以通过使用自定义微帧和使用FrameAxis作为迭代探索性分析工具来整合到FrameAxis中。此外,我们提出了在单个单词和文档级别解释FrameAxis结果的方法。我们的方法可以加速跨学科框架的可扩展和复杂的计算分析。
Framing is a process of emphasizing a certain aspect of an issue over the others, nudging readers or listeners towards different positions on the issue even without making a biased argument. Here, we propose FrameAxis, a method for characterizing documents by identifying the most relevant semantic axes (“microframes”) that are overrepresented in the text using word embedding. Our unsupervised approach can be readily applied to large datasets because it does not require manual annotations. It can also provide nuanced insights by considering a rich set of semantic axes. FrameAxis is designed to quantitatively tease out two important dimensions of how microframes are used in the text. Microframe bias captures how biased the text is on a certain microframe, and microframe intensity shows how prominently a certain microframe is used. Together, they offer a detailed characterization of the text. We demonstrate that microframes with the highest bias and intensity align well with sentiment, topic, and partisan spectrum by applying FrameAxis to multiple datasets from restaurant reviews to political news. The existing domain knowledge can be incorporated into FrameAxis by using custom microframes and by using FrameAxis as an iterative exploratory analysis instrument. Additionally, we propose methods for explaining the results of FrameAxis at the level of individual words and documents. Our method may accelerate scalable and sophisticated computational analyses of framing across disciplines.
DOI: 10.1073/pnas.1720347115
发表时间: 2018-04-17
影响因子: 11.1
作者:
Garg, Nikhil;Schiebinger, Londa;Zou, James
通讯作者: Zou, James
DOI: 10.1007/s12160-011-9308-7
发表时间: 2012-02-01
影响因子: 3.8
作者:
Gallagher, Kristel M.;Updegraff, John A.
通讯作者: Updegraff, John A.
DOI: 10.2307/1914185
发表时间: 1979-01-01
期刊: ECONOMETRICA
影响因子: 6.1
作者:
KAHNEMAN, D;TVERSKY, A
通讯作者: TVERSKY, A
DOI: 10.1111/1540-5907.00051
发表时间: 2003-10-01
影响因子: 4.2
作者:
Druckman, JN;Nelson, KR
通讯作者: Nelson, KR
DOI: 10.1177/0003122419877135
发表时间: 2019-09-25
影响因子: 9.1
作者:
Kozlowski, Austin C.;Taddy, Matt;Evans, James A.
通讯作者: Evans, James A.