Publication

Abstract : With the evolution of internet, author profiling has become a topic of great interest in the field of forensics, security, marketing, plagiarism detection etc. However the task of identifying the characteristics of the author just based on a text document has its own limitations and challenges. This paper reports on the design, techniques and learning models we adopted for the PAN-2014 Author Profiling challenge. To identify the age and gender of an author from a document we employed ensemble learning approach by training a Random Forest classifier with the training data provided by PAN organizers for English language only. Our work indicate that readability metrics, function words and structural features play a vital role in identifying the age and gender of an author.