WikiFactMine: Textmining Open Access bioscience literature - Thomas Arrow at WikidataCon 2017
From Ewan McAndrew
- Presenter: Thomas Arrow ([email protected])
- Recorded by Chaos Computer Club at the Tagesspiegel, Berlin for WikidataCon 2017 on Saturday 28 October 2017.
- Original source: https://media.ccc.de/v/wikidatacon2017-10011-wikifactmine
The WikiFactMine project is a WMF Project Grant Funded Project by ContentMine that seeks to use text mining of the Open Access bioscience literature to enhance the Wikimedia projects. This workshop is a hands on introduction to the tools the project has made and how you can get involved. Both to enhance the mining of the topics in which you are interested by creating dictionaries from Wikidata itself and also by using the facts linked to Wikidata that we've already mined to enhance Wikimedia projects including Wikidata.
We'll be giving a brief introduction to the project including: the selection of papers we mine, how the mining is being done and the sort of things we're extracting. We'll briefly show the tools we both use and have developed and how you could get involved or contribute to their development.
We'll then show how to make dictionaries and make some in the session using tools we've developed. Finally we'll be showing the way you can use the facts we've mined through the wikifactmine-api, our userscript and through other 3rd party tools.