Linguistic profiling and behavioral drift in chat bots

Nawaf Ali, University of Louisville
Derek Schaeffer, University of Louisville
Roman V. Yampolskiy, University of Louisville

Abstract

When trying to identify the author of a book, a paper, or a letter, the object is to detect a style that distinguishes one author from another. With recent developments in artificial intelligence, chat bots sometimes play the role of the text authors. The focus of this study is to investigate the change in chat bot linguistic style over time and its effect on authorship attribution. The study shows that chat bots did show a behavioral drift in their style. Results from this study imply that any non-zero change in lingual style results in difficulty for our chat bot identification process.