Automatic IQ Estimation Using Stylometric Methods
Authors:
- 1 January 2019
- book chapter
- Published by IGI Global Scientific Publishing
- p. 32-45
Abstract
Stylometry is a study of text linguistic properties that brings together various fields of research such as statistics, linguistics, computer science and more. Stylometry methods have been used for historic investigation, as forensic evidence and an educational tool. This chapter 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 indexes 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 studies that focus on using stylometry methods to estimate individual's intelligence. Perhaps this work presents the first in-depth attempt to do so.Keywords
This publication has 7 references indexed in Scilit:
- Language and Discourse Analysis with Coh-Metrix: Applications from Educational Material to Learning Environments at ScaleJournal of Learning Analytics, 2016
- Automated Evaluation of Text and Discourse with Coh-Metrix2014
- Coh-MetrixEducational Researcher, 2011
- MTLD, vocd-D, and HD-D: A validation study of sophisticated approaches to lexical diversity assessmentBehavior Research Methods, 2010
- The “Other IQ”: Historiometric Assessments of Intelligence and Related ConstructsReview of General Psychology, 2009
- Linguistic Features of Writing QualityWritten Communication, 2009
- Coh-Metrix: Analysis of text on cohesion and languageBehavior Research Methods, Instruments, & Computers, 2004