Replication Data for: Improving the Selection of News Reports for Event Coding Using Ensemble Classification

We introduce an automatic classification system to eliminate irrelevant source material for the coding of political event data from global news-wires. Our pipeline relies on a high-performance supervised heterogeneous ensemble classifier working on extremely unbalanced training classes. The output is then supplied to human coders for further information extraction, creating a semi-automatic pipeline. The package includes the software required to train and test the classifier, as well as documentation on how to use it.本研究提出一种自动分类系统，用于在对全球新闻专线来源的政治事件数据进行编码时，剔除无关的源材料。本流程依托一款可在训练类别极度不平衡场景下运行的高性能监督式异构集成分类器（supervised heterogeneous ensemble classifier），将其输出结果交由人工编码人员开展进一步的信息抽取工作，由此构建出一套半自动处理流程。本软件包包含训练与测试该分类器所需的全部软件，同时附带了详细的使用说明文档。