Here you can find our machine learning models as well as the datasets used on our published work

FIGHT – Corpus of Portuguese Tweets

Please note that the corpus does not contain the tweet Text, due to the restrictions imposed by Twitter. The text can be obtained by fetching the tweet directly from the Twitter API.

Golden Set – Annotated by 5 different people

The final annotation value corresponds to a minimum agreement of two annotators for a given tag.

Models

Coming Soon …