Your software must generate a file with a line for each document of the dataset with the following information separated by commas (the same format as the truth file provided in the training corpus):

Author id, gender, age, variety

For example, the following line:


Corresponds to author 5, who is a female under 25 and uses the variety from Qatar.

In order to encourage the investigation of different kinds of features, three runs per participant are allowed.

You can submit your runs by sending the generated files to (at) gmail (dot) com with your full name.