Code for [ICWSM’20] and [CSCW’18].
The code repository to replicate our results and figures.
(Dis)belief dataset used in [ICWSM’20].
The dataset contains 6,000+ tweets annotated with belief and disbelief labels.
User Comments dataset used in [ICWSM’20] and [CSCW’18].
The dataset contains 2,600,000+ social media comments in reply to above posts.
facebook youtube twitter
Social Media Posts dataset used in [CSCW’18].
The dataset contains 5,000+ social media posts and their veracity judged by Snopes or PolitiFact.
ComLex lexicon used in [CSCW’18].
The lexicon contains 300 categories but only the top 56 named ones are human validated.