The evaluation metric for this competition is F1-Score. The F1 score is the harmonic mean of precision p and recall r. Precision is the ratio of true positives (tp) to all predicted positives (tp + fp). Recall is the ratio of true positives to all actual positives (tp + fn). The F1 score is given by:
\[ F1 = 2\frac{p \cdot r}{p+r}\ \ \mathrm{where}\ \ p = \frac{tp}{tp+fp},\ \ r = \frac{tp}{tp+fn} \]
The F1 score weights recall and precision equally, and a good classification algorithm will maximize both precision and recall simultaneously. Thus, moderately good performance on both will be favored over extremely good performance on one and poor performance on the other.
Output format
Each line in the output file should contain two fields, separated by a comma as below:
TweetID,Label
where TweetID is the id of the tweet from the test file and Label is either 0 or 1. Please refer to the sample_output.txt file for an example.
Note: The file should contain the column names file above. Please follow the format in the sample_output.txt file provided.