##Files
All teams are provided with the following files - training dataset (**train.csv**) and test dataset (**test.csv**).

##Training dataset
- ```tweet``` - (character) a string of letters and symbols representing a tweet
- ```sentiment``` - (integer) an integer representing a sentiment corresponding to a tweet: 1 indicates *negative* sentiment, 2 indicates *neutral*, 3 indicates *positive*

##Test dataset
- ```id``` - (integer) id corresponding to a tweet in the test dataset
- ```tweet``` - (character) a string of letters and symbols representing a tweet which sentiment needs to be predicted