首页> 外文OA文献 >How Polarized Have We Become? A Multimodal Classification of Trump Followers and Clinton Followers
【2h】

How Polarized Have We Become? A Multimodal Classification of Trump Followers and Clinton Followers

机译:我们如何变得极化?特朗普的多式联运分类   追随者和克林顿粉丝

代理获取
本网站仅为用户提供外文OA文献查询和代理获取服务,本网站没有原文。下单后我们将采用程序或人工为您竭诚获取高质量的原文,但由于OA文献来源多样且变更频繁,仍可能出现获取不到、文献不完整或与标题不符等情况,如果获取不到我们将提供退款服务。请知悉。

摘要

Polarization in American politics has been extensively documented andanalyzed for decades, and the phenomenon became all the more apparent duringthe 2016 presidential election, where Trump and Clinton depicted two radicallydifferent pictures of America. Inspired by this gaping polarization and theextensive utilization of Twitter during the 2016 presidential campaign, in thispaper we take the first step in measuring polarization in social media and weattempt to predict individuals' Twitter following behavior through analyzingones' everyday tweets, profile images and posted pictures. As such, we treatpolarization as a classification problem and study to what extent Trumpfollowers and Clinton followers on Twitter can be distinguished, which in turnserves as a metric of polarization in general. We apply LSTM to processingtweet features and we extract visual features using the VGG neural network.Integrating these two sets of features boosts the overall performance. We areable to achieve an accuracy of 69%, suggesting that the high degree ofpolarization recorded in the literature has started to manifest itself insocial media as well.
机译:数十年来,美国政治中的两极分化已得到广泛记录和分析,在2016年总统大选期间,这一现象变得更加明显,特朗普和克林顿描绘了两幅截然不同的美国图片。受2016年总统大选期间这种巨大的两极分化和Twitter广泛使用的启发,在本文中,我们迈出了衡量社交媒体两极分化的第一步,并试图通过分析人们的日常推文,个人资料图像和张贴的图片来预测个人Twitter的行为。因此,我们将极化视为分类问题,并研究可以在多大程度上区分Twitter上的Trumpfollowers和Clinton追随者,而反过来又可以将其作为极化的度量。我们将LSTM应用于处理推特特征,并使用VGG神经网络提取视觉特征,将这两组特征整合在一起可以提高整体性能。我们能够达到69%的准确度,这表明文献中记录的高度极化也已经开始在社交媒体中体现出来。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
代理获取

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号