Given a message, classify whether the message is of positive, negative, or neutral sentiment.
We will replace the measure used in 2016 (F1 averaged across the positives and the negatives) with macro-averaged recall (recall averaged across the three classes), since the latter has better theoretical properties than the former, and since this provides better consistency with Subtask B
Please note that by downloading the Twitter data you agree to abide by the Twitter terms of service (https://twitter.com/tos)
Start: Aug. 1, 2016, midnight
Start: Jan. 16, 2017, midnight
Jan. 22, 2017, 11:59 p.m.
You must be logged in to participate in competitions.Sign In