Classification of News according to Age Groups Using NLP

Abstract

In this study, it is aimed to label the news in electronic media according to age groups by using Natural Language Processing. The selected ones for training in the news dataset collected from the news sites were processed in Python language using the NLP Zemberek Library, and a vocabulary dictionary that could represent Childhood, Adolescence and Adult age groups of Havighurst's Development Theory adapted to the current situation was created (which age group of each word as appropriate). A classifier was then proposed to determine the classes of the news dataset selected for testing using this dictionary. As a result of the tests, it was seen that the developed dictionary can detect the correct class with a success rate of 0.70.

Keywords

• news age group detection
• age group dictionary
• zemberek
• natural language processing