twitter-news

A collection of tweets scraped from Twitter since January 2020 using the search parameter "news". The resulting json file was then separated into 2 separate `.csv` files. One contains the tweets, whereas the other contains the network analysis inputs.

The associated network analysis file is a document containing all the nodes and edges derived from the interactions in the tweets as follows:

Nodes, all distinct tweeters including mentions
Edges, defined as when one user mentions another user in a tweet or replies
Weight, number of time the edge interaction has taken place

Here is some code to get started- https://github.com/datadoctor100/twitter_analysis

自2020年1月起，通过使用“新闻”搜索参数从Twitter上抓取的一系列推文构成了一个数据集。随后，生成的JSON文件被分割成两个单独的`.csv`文件。其中一个文件包含推文内容，而另一个文件则包含网络分析输入。相关的网络分析文件记录了以下所有节点和边：
节点，包括所有不同的推文作者以及提及的用户
边，定义为当一位用户在推文中提及或回复另一位用户时
权重，表示边交互发生的次数

以下是一段用于入门的代码示例：https://github.com/datadoctor100/twitter_analysis