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: neves-silva@inknow.pt