The Twitter Academia API was used to search for tweets with the phrase "you are a bot"; 122299 tweets from June 2016 to June 2021 were collected, these are named the declaration set. The code to collect the data is available in the data under the "dissertation code" folder - java was used to pull data from twitter's academic API.

The surrounding "threads" of the tweets were collected for contextual conversation data; 112294 tweets were collected, and they are named the control set. 

The results of the clustering are also enclosed, the process used to create the clusters are in the java code uploaded