Artificial intelligence powered personality assessment: A multidimensional psychometric natural language processing perspective

Recent technological advances have allowed researchers to apply automated, language-based machine learning models as alternatives to self-reports for assessing personality. However, previous work has largely overlooked the multidimensional nature of personality and lacked in-depth exploration of validity issues. In this dissertation, I examined novel methods for leveraging artificial intelligence (AI), natural language processing (NLP), machine learning, and automation to systematically glean personality-related information from textual data which offers rich information and reflects various aspects of personality but has been severely underutilized. In two studies, I connected the five-factor (or Big Five) model (comprised of openness to new experiences, conscientiousness, extraversion, agreeableness, and neuroticism) with NLP from two angles: 1) a construct validity perspective (i.e., the degree to which information extracted from textual data reflects personality constructs), and 2) an applicability perspective (i.e., the ability to elicit personality-relevant information from text in line with psychological and organizational principles). In Study 1, I meta-analytically reviewed the multidimensional psychometric evidence of AI-supported language-based personality assessment. Results showed that measurement reliability is often not addressed in past AI personality assessment research, and that construct validity evidence is lacking. In Study 2, I built an interactive tool to automatically and adaptively prompt for, collect, and analyze personality-relevant topic-based (i.e., honoring the Big Five factorial structure) narrative data through conversations conducted by an AI chatbot. Results showed some improvements in various validities of the new personality assessment tool. Potential reasons for the improvement magnitudes, limitations of the current methods, and future directions are discussed.

Name thesis:degree_name

Ph.D.

Level thesis:degree_level

Dissertation

Discipline thesis:degree_discipline

Psychology

Grantor

University of Illinois at Urbana-Champaign

Year dc:date

2022

Author dc:creator

• Sun, Tianjun

Contributors dc:contributor

• Drasgow, Fritz
• Roberts, Brent W
• Rounds, James
• Guenole, Nigel
• Jiang, Ge

• personality
• psychometrics
• machine learning
• natural language processing
• artificial intelligence

Statement dc:rights

• Copyright 2021 Tianjun Sun

Language dc:language

en

Handle dc:identifier

http://hdl.handle.net/2142/113136

OAI identifier oai:identifier

oai:www.ideals.illinois.edu:2142/113136