Quantifying Perceived Political Bias of Newspapers through a Document Classification Technique

IF 0.7 2区文学 0 LANGUAGE & LINGUISTICS

Journal of Quantitative Linguistics Pub Date : 2020-06-16 DOI:10.1080/09296174.2020.1771136

Hyungsuc Kang, Janghoon Yang

引用次数: 8

Abstract

ABSTRACT Even though a certain degree of political bias is unavoidable in the media, strong media bias is likely to have an impact on society, especially on the formation of public opinion. This research proposes a data-driven method for quantifying political bias of media contents. With a document classification technique called doc2vec and social data from Facebook posts, a model for analysing the bias is developed. By applying the model to contents of major South Korean newspapers, this paper demonstrates quantitatively that significant political bias exists in the newspapers in line with the perceived political bias.

查看原文本刊更多论文

通过文件分类技术量化报纸的感知政治偏见

尽管媒体中存在一定程度的政治偏见是不可避免的，但强烈的媒体偏见很可能对社会产生影响，尤其是对舆论的形成。本研究提出一种数据驱动的方法来量化媒体内容的政治偏见。通过一种名为doc2vec的文档分类技术和来自Facebook帖子的社交数据，开发了一个分析偏见的模型。通过将该模型应用于韩国主要报纸的内容，本文定量地证明了报纸中存在显著的政治偏见，这与感知到的政治偏见一致。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Journal of Quantitative Linguistics Multiple-

CiteScore

2.90

自引率

7.10%

发文量

期刊介绍： The Journal of Quantitative Linguistics is an international forum for the publication and discussion of research on the quantitative characteristics of language and text in an exact mathematical form. This approach, which is of growing interest, opens up important and exciting theoretical perspectives, as well as solutions for a wide range of practical problems such as machine learning or statistical parsing, by introducing into linguistics the methods and models of advanced scientific disciplines such as the natural sciences, economics, and psychology.