POLECAT Weekly Data

The POLitical Event Classification, Attributes, and Types (POLECAT) dataset is the successor event dataset to the Integrated Crisis Early Warning System (ICEWS). Event data consists of coded interactions between socio-political actors (i.e., cooperative or hostile actions between individuals, groups, sectors, and nation states). POLECAT uses a newly developed, machine-learning coder based on the Political Language Ontology for Verifiable Event Records (PLOVER) ontology to produce an event database by analyzing news stories in seven languages from over one-thousand sources across the globe. The database includes millions of time-stamped, geolocated events from 2018 onward, is updated hourly, and posted weekly. Each event includes several attributes, as defined in the included POLECAT Dictionary and PLOVER Manual. Please see the companion POLECAT Dataverse page at <a href="https://doi.org/10.7910/DVN/LMFPIP">doi.org/10.7910/DVN/LMFPIP</a> for associated documentation.

政治事件分类、属性与类型（Political Event Classification, Attributes, and Types, POLECAT）数据集是综合危机预警系统（Integrated Crisis Early Warning System, ICEWS）的后续事件数据集。事件数据由经编码的社会政治行动者间互动构成，即个体、群体、部门与民族国家之间的合作或敌对行动。POLECAT依托全新开发的、基于可验证事件记录政治语言本体论（Political Language Ontology for Verifiable Event Records, PLOVER）的机器学习编码器，通过分析覆盖全球的逾1000个信息源的7种语言新闻报道，构建事件数据库。该数据库收录了2018年以来的数百万条带时间戳、经地理定位的事件，支持每小时更新、每周发布。每条事件均包含多项属性，相关定义详见随附的《POLECAT词典》与《PLOVER手册》。如需获取相关文档，请访问配套的POLECAT Dataverse页面：<a href="https://doi.org/10.7910/DVN/LMFPIP">doi.org/10.7910/DVN/LMFPIP</a>。

搜集汇总

背景与挑战

背景概述

POLECAT Weekly Data是一个政治事件分类数据集，使用机器学习技术分析全球新闻故事，记录社会政治行为体之间的互动。数据集包含2018年以来的时间戳和地理定位事件，每周更新，涵盖七种语言和上千个新闻来源。