Improving the selection of news reports for event coding using ensemble classification

Improving the selection of news reports for event coding using ensemble classification
复制标题

使用集成分类改进事件编码的新闻报道选择

DOI:
--
复制
发表时间:
2015
期刊:
影响因子:
--
通讯作者:
Nils B. Weidmann
Nils B. Weidmann
中科院分区:
--
文献类型:
--
作者:
Mihai Croicu;Nils B. Weidmann

文献摘要

参考文献

被引文献

相似文献

对新闻报道中的政治事件进行手动编码非常昂贵且耗时,而完全自动编码在收集数据的精度和粒度方面存在局限性。在本文中,我们通过建立半自动管道引入了一种替代策略,其中自动分类系统在人类进行进一步编码之前消除了不相关的源材料。我们的管道依赖于高性能监督异构集成分类器,该分类器在极其不平衡的训练类上工作。该系统部署到抗议独裁大规模动员数据库后,能够将需要人工编码的源文章数量减少一半以上,同时保留超过 90% 的相关材料。
Manual coding of political events from news reports is extremely expensive and time-consuming, whereas completely automatic coding has limitations when it comes to the precision and granularity of the data collected. In this paper, we introduce an alternative strategy by establishing a semi-automatic pipeline, where an automatic classification system eliminates irrelevant source material before further coding is done by humans. Our pipeline relies on a high-performance supervised heterogeneous ensemble classifier working on extremely unbalanced training classes. Deployed to the Mass Mobilization on Autocracies database on protest, the system is able to reduce the number of source articles to be human-coded by more than half, while keeping over 90% of the relevant material.
DOI: 10.1007/3-540-45014-9
发表时间: 2000-06
期刊: --
影响因子: --
作者:
Thomas G. Dietterich
通讯作者: Thomas G. Dietterich