Important Note: All of the User IDs and Tweet IDs Are Anonymized. No Personal Info Is Disclosed in the Datasets Publicized Here.
Please note that the row number (index) of "User Timeline (Tweets) Dataset" matches that on the "Tweet Embeddings" when all the embedding parts are merged together. In other words, the i_th row in the Tweets Dataset represents the metadata (e.g. disorder, retweet count, like count, etc.) of the i_th row in the embeddings dataset that has the embeddings of the actual tweet text.