Date on Master's Thesis/Doctoral Dissertation


Document Type

Master's Thesis

Degree Name



Computer Engineering and Computer Science

Degree Program

Computer Science, MS

Committee Chair

Yampolskiy, Roman

Committee Co-Chair (if applicable)

Imam, Ibrahim

Committee Member

Imam, Ibrahim

Committee Member

Losavio, Michael

Author's Keywords

stylometry; artificial intelligence; aI; IQ; natural language processing; NLP


Stylometry is a study of text linguistic properties that brings together various field of research such as statistics, linguistics, computer science and more. Stylometry methods have been used for historic investigation, as forensic evidence and educational tool. This thesis presents a method to automatically estimate individual’s IQ based on quality of writing and discusses challenges associated with it. The method utilizes various text features and NLP techniques to calculate metrics which are used to estimate individual’s IQ. The results show a high degree of correlation between expected and estimated IQs in cases when IQ is within the average range. Obtaining good estimation for IQs on the high and low ends of the spectrum proves to be more challenging and this work offers several reasons for that. Over the years stylometry benefitted from wide exposure and interest among researches, however it appears that there aren’t many studies that focus on using stylometry methods to estimate individual’s intelligence. Perhaps this work presents the first in-depth attempt to do so