Automatic Text Classification is to automatically classify a text document according to a set of pre-defined classes, using a machine learning technique.
In this project, the gender and age of authors are predicted. A naive Bayes classifier is handled as a machine learning technique and train it with the PAN2013 dataset.
Features related to author profiling like content based features and stylistic features are investigated and implemented .
###Notes: -To execute the age_gender_classifier.py, you need to have the 'en' folder from PAN dataset in the project folder
-To execute the evaluation.py, you need to have the 'pan13-test-corpus1\en' or the folder 'pan13-test-corpus2\en' from PAN dataset in the project folder