Multifaceted Online Coordinated Behavior in the 2020 US Presidential Election

This dataset contains ~140M tweets related to the 2020 United States Presidential Election, published and collected between October 2, 2020, and December 2, 2020. In addition, we provide nodes and edges of the superspreader user similarity network, as described in the paper below.

Tardelli, S., Nizzoli, L.,  Avvenuti, M., Cresci, S., & Tesconi, M. Multifaceted Online Coordinated Behavior in the 2020 US Presidential Election.

In detail, the dataset consists of:

tweet-ids.csv.zip: a CSV file with the column "tweet_id," containing 11,264,820 tweet IDs related to the 2019 United Kingdom General Election, published and collected between November 12, 2019, and December 12, 2019.

user_similarity_nework_nodes.csv: a CSV file with the columns "id" and "cluster," relating to the nodes of the superspreader user similarity network mentioned in the paper.

user_similarity_nework_edges.csv: a CSV file with the columns "source," "target," "weight," and "alpha" relating to the edges of the superspreader user similarity network mentioned in the paper.

本数据集包含约1.4亿条与2020年美国大选（2020 United States Presidential Election）相关的推文，采集与发布时间为2020年10月2日至2020年12月2日。此外，我们还提供下文论文中所述的超级传播者用户相似度网络（superspreader user similarity network）的节点与边信息。

该论文为Tardelli, S.、Nizzoli, L.、Avvenuti, M.、Cresci, S. 与 Tesconi, M. 合著的《2020年美国大选中的多维度在线协同行为（Multifaceted Online Coordinated Behavior in the 2020 US Presidential Election）》。

具体而言，本数据集包含以下文件：
1. tweet-ids.csv.zip：包含"tweet_id"字段的CSV压缩文件，内含11264820条与2019年英国大选（2019 United Kingdom General Election）相关的推文ID，采集与发布时间为2019年11月12日至2019年12月12日。
2. user_similarity_nework_nodes.csv：包含"id"与"cluster"字段的CSV文件，对应本文所述的超级传播者用户相似度网络的节点信息。
3. user_similarity_nework_edges.csv：包含"source"、"target"、"weight"与"alpha"字段的CSV文件，对应本文所述的超级传播者用户相似度网络的边信息。