Replication Data for: Variation across Scales: Measurement Fidelity under Twitter Data Sampling

The dataset is first introduced in the following paper: Siqi Wu, Marian-Andrei Rizoiu, and Lexing Xie. Variation across Scales: Measurement Fidelity under Twitter Data Sampling. In AAAI International Conference on Weblogs and Social Media (ICWSM), 2020. Complete/Sample retweet cascades datasets These datasets contain 2 pairs of complete/sampled retweet cascades on topic Cyberbullying (sampling rate: 0.5272) and YouTube (sampling rate: 0.9153). Each line is a cascades for a root tweet, in the format of "root_tweet_id-root_user_followers:retweet_id1-retweet_user_followers1,retweet_id2-retweet_user_followers2,...". The tweet_id can be melt into timestamp_ms, check the melt_snowflake function here. See more details in this github repo.