An Author Profiling Approach Based on Language-dependent Content and Stylometric Features

Abstract

We describe the approach that we submitted to the 2015 PAN competition for the author profiling task. The task consists in predicting some attributes of an author analyzing a set of his/her Twitter tweets.We consider several sets of stylometric and content features, and different decision algorithms: we use a different combination of features and decision algorithm for each language-attribute pair, hence treating it as an individual problem.

Publication
Uncovering Plagiarism, Authorship and Social Softare Misuse at Conference and Labs of the Evaluation Forum