magnet - Automatic Recommendation of In-Context Media Content to Support Exploratory Research in Journalism

magknet has indirectly received funding from the European Union’s Horizon 2020 research and innovation action programme, via the AI4Media Open Call #2 issued and executed under the AI4Media project (Grant Agreement no. 951911).

project website: https://www.magknet.com/

The data shared in this folder is the core of the magknet application in the format of 5 sql tables:

* common - list of common words in English used as stop list.* fundamental - list of 17 fundamental topics based on the IPTC classification (https://iptc.org/)* term - list of keywords referencing the respective fundamental topic and its relative frequency.* concept - list of concepts used to map the context based on (where/when/who/what) in an hierachical structure* context - context ontology in an hierachical structure referencing the respective concept   (multiple means that the term is composed by multiple words; type and validated are to be ignored)

for more information, please contact: [e-mail]

magknet 已通过欧盟地平线2020（Horizon 2020）研究与创新行动计划，经由AI4Media项目发起并执行的AI4Media公开征集第2号（AI4Media Open Call #2）间接获得资助，资助协议编号为951911。

项目官网：https://www.magknet.com/

本文件夹中共享的数据为magknet应用的核心内容，以5张SQL表的格式存储：
* common：英语常用停用词表——收录用作停用词列表的英语通用词汇。
* fundamental：基于IPTC分类体系的17个核心主题列表（https://iptc.org/）
* term：关键词列表——收录指向对应核心主题及其相对词频的关键词。
* concept：层级化结构概念列表——收录基于「何地/何时/何人/何事」维度映射上下文的概念。
* context：上下文本体——收录指向对应概念的层级化结构上下文本体（注：「multiple」表示该术语由多个词汇构成；「type」与「validated」字段可忽略）。

如需了解更多信息，请联系：[e-mail]