full-corpus.csv Report
You are being provided with a data set of 5113 tweets in a file (full-corpus.csv). This is a comma-separated value file (.csv) which is a human-readable file type in which each line contains data. Pieces of data are separated by a comma, and for this data set, there are five pieces of data (i.e., fields) per line. You can open up the file in any text editor (e.g., Sublime) or even Excel if you want to look at the data directly (and you should always inspect your data!). The first line contains the name of the fields: “Topic” (what is this tweet about?), “Sentiment” (is this tweet positive about that topic, negative, neutral, or irrelevant?), “TweetId” (a unique ID used by Twitter – all of these will be different), “TweetDate” (when did this get tweeted?), and “TweetText” (what did the tweet actually say?).