Another problem with this data right now is that there are lots of interesting pieces of information hidden inside the
tweet_text column, for example, consider all the times that a person directs a tweet to the attention of another person using the
@ symbol before their username. This is called a mention on Twitter. It might be interesting to count how many times a particular person is mentioned or how many times they are mentioned in conjunction with a particular keyword. Another interesting piece of data hidden in some of the tweets is hashtags; for example, the tweet with ID 2165 discusses the concepts of jobs and babysitting using the
This same tweet also ...