Overview of the 3rd Author Profiling Task at PAN 2015

This overview presents the framework and the results for the Author Profiling shared task at PAN 2015. This year task aims at identifying age, gender and personality traits of Twitter users. With the help of an online personality test\footnote{In order to address ethical and privacy issues, authors were asked for their permission to use the tweets when answering the personality test. The dataset was anonymised, password protected, and released to task participants only.} a dataset was collected from Twitter with annotations about age, gender and Big Five personality traits in four different languages: English, Spanish, Italian and Dutch. The approaches of 22 participants and their results are presented.