Skip to content
Go to file


Analysis of controversial tweets This project also introduces a lexicon which can be used to classify the URL into the following categories:

Type​ Counts​ Description​ Example​
Blog​ 194​ All blogging platforms indexed in Wikidata​​
Commercial​ 55​ All commercial websites indexed in Wikidata​​
Fake news​ 518​ 1) A list developed by Melissa Zimdars and her research team at Merrimack College
​2) A list of fake news websites from Wikipedia
​3) FakeNewsChecker​​
News​ 1,988​ 1) News sources indexed by Wikidata
​2) List of trusted news domains created by Facebook ​​
Scientific​ 2,962​ All scientific publishers indexed by Wikidata​​
Social media​ 87​ All social media domains indexed by Wikidata​​
Twitter​ 1​ Links to other tweets, twitter hosted images, videos​​
Videos​ 13​ All video sharing services from Wikipedia​​

Click to access the URL categorization lexicon.


If you are using this lexicon please cite the following papers:

Addawood, A., Rezapour, R., Mishra, S., Schneider, J., & Diesner, J. (2017). Developing an Information Source Lexicon. In NIPS workshop on Prioritising Online Content. Retrieved from

  title = {Developing an Information Source Lexicon},
  author = {Addawood, Aseel and Rezapour, Rezvaneh and Mishra, Shubhanshu and Schneider, Jodi and Diesner, Jana},
  year = {2017},
  booktitle = {NIPS workshop on Prioritising Online Content},
  url = {}

Process URLs

  • Extract urls using Merge URLs and tweets.ipynb
  • Fix expanded URLs using Fix expanded URL errors.ipynb
  • Process URL categories using Process URL categories.ipynb
  • Fix files which don't have parallel structure using Fix vaccine files.ipynb
  • Merge URLs using Merge URLs and tweets.ipynb
  • Run Prepare analysis data.ipynb by uncommenting the Location blog



Analysis of controversial tweets




No releases published


No packages published