Author Identification on Anonymous Regional Literature

Abstract

Abstract: In order to identify the author of a given text, researchers have used many different methods. One such method is forensic linguistics which examines stylistic and content-based aspects of a text in an effort to determine who wrote it. Another area where author identification is often useful is bot detection; this involves identifying automated accounts on social media or other websites. Finally, marketing research can also be utilized for identifying the authors behind advertisements. Despite significant progress having been made with English texts, there remains much work to be done when it comes to regional variations in language use. In this study, we aim to build a machine learning model that will be able to identify the probable author of the provided anonymous text using various lexical and syntactic variables of the literature.