Exercise 2: Variables, Measurement, and Hypotheses (10 points)

The Russian Influence operation tweets in the last example were generated by a total of 3,520 fake accounts. The following dataset

of the accounts (rather than of the tweets) has been created so that we may take a closer look at their characteristics.

R Output for Structure of User Dataset

tibble [3,520 x 6] (S3: tbl_df/tbl/data.frame)

$ userid

: chr [1:3520] "+1zrIfSEu5GaeTzWgVgrPS6MiddJ55u5JXI5vuGzUY=" "+9JIfRUrH1ZK+6UXd9kovs87ugSJpXFs6lZsSG526Bw="

"+cMaDi6JD3MhrhNUUwd6g4lCgZhH8UWs65fOHU4ItpE=" "+dibMDmcNJdwXTOwwedM4ZVYRHGASwEjWFrNLdt4Clk=" ...

$ tweet_count: int [1:3520] 178 191 8 7 1 2 109 3 2 4 ...

$ followers : num [1:3520] 105 54 71 218 88 ...

$ following : num [1:3520] 141 121 184 313 505 ...

$ max_likes : num [1:3520] 1 2 2 0 0 0 0 1 0 0 ...

$ max_retweet: num [1:3520] 1 2 2 0 0 0 0 1 0 0 ...

You'll notice that some new variables have been generated. Below are the descriptions of the variables in the dataset.

Variable Descriptions

userid: account identifier

tweet_count: the total number of tweets for each account

followers: the total number of followers for each account

following: the total number of other accounts followed by each account

max_likes: the highest number of likes reported across all of the account's tweets

max_retweet: the highest number of retweets (shares) reported across all of the account's tweets

View answer and explanation