##Performance Metric
The performance of the algorithms will be evaluated based on *classification accuracy* (the ratio between the number of correctly classified samples to the total number of samples). Randomly assigning labels to the tweets in the test dataset gives an accuracy of approximately 30%.

##Leaderboards
Kaggle will calculate the accuracy on two subsets of the test dataset - *public* and *private*. The *public* leaderboard will be available during the competition while the *private* leaderboard will only be available at the end of the competition.