Dataset Containing Online Communities Metadata

Sets of statistics derived from posts to two sets of online forums, each serving an ideological community. The posts were grouped into six-month time slices; four consecutive time slices were analysed for Community A, and one time slice for Community B. The quantities measured relate to the textual content of users' posts, their level of participation in threads, and the network of other users to whom they are connected by replies and quoting. The data were collected in 2011-2012 as part of an internal project.The data were collected by screen-scraping publicly visible online community forum posts. Further details are available in the README file.Last two years (Community A) and six months (Community B) taken from SQL database of full scrape. Content removed. Sub-forum names obfuscated. User IDs MD5 encoded.The data are encoded as comma-separated value files