arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2011.06844cs.CL
收藏

网络内容宣传分类的跨域学习

Cross-Domain Learning for Classifying Propaganda in Online Contents

Shandong University(山东大学);Hasso Plattner Institute(哈索·普拉特纳研究所);University of Potsdam(波茨坦大学)

Liqiang Wang, Xiaoyu Shen, Gerard de Melo, Gerhard Weikum

摘要:

随着新闻和社交媒体呈现出越来越多的操纵性极化内容,检测此类宣传作为内容分析的新任务受到关注。以前的工作集中在监督学习与训练数据从同一领域。然而,由于宣传可能是微妙的,并不断发展,人工识别和适当的标签是非常苛刻的。因此,训练数据是主要瓶颈。在本文中,我们解决了这一瓶颈,并提出了一种利用跨领域学习的方法,该方法基于来自新闻和推文的标记文档和句子,以及政治演讲,其宣传程度有明显差异。我们设计信息功能,并建立各种分类器的宣传标签,使用跨域学习。我们的实验证明了这种方法的实用性,并确定在各种配置的源和目标的转移步骤的困难和限制。我们进一步分析了各种特征的影响,并描述了宣传的突出指标。

英文摘要:

As news and social media exhibit an increasing amount of manipulative polarized content, detecting such propaganda has received attention as a new task for content analysis. Prior work has focused on supervised learning with training data from the same domain. However, as propaganda can be subtle and keeps evolving, manual identification and proper labeling are very demanding. As a consequence, training data is a major bottleneck. In this paper, we tackle this bottleneck and present an approach to leverage cross-domain learning, based on labeled documents and sentences from news and tweets, as well as political speeches with a clear difference in their degrees of being propagandistic. We devise informative features and build various classifiers for propaganda labeling, using cross-domain learning. Our experiments demonstrate the usefulness of this approach, and identify difficulties and limitations in various configurations of sources and targets for the transfer step. We further analyze the influence of various features, and characterize salient indicators of propaganda.

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。

↑