Artificial Intelligence (AI) and its Potential in Personality Assessment and Projective Testing

        Despite copious criticisms and drawbacks leveled against Artificial Intelligence (AI) over recent years, the field of Psychology continues to realize the emergent potential of machine learning and AI across most sub-disciplines within its purview (Botvinick, 2022; Dwyer et al., 2018; Gado et al., 2022; Murphy, 2022, Piotrowski, 2025). An online keyword search of PsycINFO revealed an extensive bibliography (nearly 12,000 articles; 600 dissertations), specific to the topic of AI. In fact, the term ‘Big Data’ has become a popular scientific moniker. But what encompasses the arena of Big Data? Researchers include source data such as biographical information, read outs from personal data garnered from modern digital technologies (i.e., sensors in wearable devices, user smartphone logs, GPS positioning, applications usage, music preferences, financial transactions, fitness data), and the cascade of data generated from social media use and interaction (Hinds & Joinson, 2024; Stachl et al., 2020). Proponents claim that visual images and personal videos provide interesting incremental information (and hypotheses?) unique to an individual (Jordan & Mitchell, 2015). Yet critics espouse caution on the validity of big data approaches that use social media text data for the assessment of personality (Alexander et al., 2020; Liou et al., 2022; Tay et al., 2022).

        Despite these concerns, others highlight the potential applications of AI for psychological assessment and mental health diagnostics (e.g., Maurya et al., 2024; O’Conno, 2024; Zhou et al., 2022). Based on scientific attributes like the incorporation of ‘Big Data’ and predictive efficacy, AI appears to be a potentially ideal methodological mechanism in the a) application to clinical data obtained via both objective and projective measures, and b) development of an assessment protocol specific to the research and clinical determinants of personality assessment. Thus, advances in machine learning models and Big Data analytics have generated profound clinical attention to the study of personality and, concomitantly, to applications in individual psychological assessment (Bleidorn & Hopwood, 2019; Fokkema et al., 2022; Iliescu et al., 2022; Stachl et al., 2020), including personality scale development.

        Recent studies suggest that AI has potential for the study of personality and, more directly, personality assessment based on biographical data, natural language processing (NLP), collateral records, and interview protocols. Hence, clinical data garnered from projective assessment could be supplemented by AI source data, such as digital traces of behavior from an individual’s social media interactions and / or ecological/ambulatory record. On a cautionary note, clinicians need to be cognizant of the fact that ‘additional’ data does not necessarily translate into an increase in incremental validity or clinical prediction. Furthermore, with the exponential advances in AI technology, clinicians will need to stay abreast of the emergent ‘big data’ literature and with novel nomenclature (e.g., visibility, veracity, random forests, value, messy matrix).

        Noteworthy, a recent special issue of the European Journal of Psychological Assessment was devoted to a discussion of the potential of AI for psychological assessment and test construction (Bibantz et al., 2024; Iliescu et al., 2022). This prompted an examination of the recent extant literature that fostered a bibliographic template on key studies on the AI-Personality Assessment nexus. An online search of articles, indexed in the database PsycINFO over recent years, on the topic of personality assessment and ‘Artificial Intelligence’ (AI) identified an emerging view of scholarship on this issue. The Table below presents a brief synopsis of studies that shed some light regarding the potential applications of AI to advances in personality assessment.

Table 1. Studies that discuss the potential of AI for the field of personality assessment

        Based on emergent research outlined above, it is quite apparent that AI technologies can have a monumental impact in the applied and social sciences pertinent to the field of personality assessment. Copious data on the individual can be amassed from various sources, including specific behavioral, social, and physical attributes evaluated via ecological and ambulatory assessment methods (Seizer et al., 2024). Yet, the inherent potential of ‘big’ data’ analyzed via machine learning/AI methods does pose serious challenges and concerns for personality researchers and practitioners. Major issues such as a) degree of incremental validity, b) efficacious outcome prediction, c) contribution of unique personality variance, d) influence of ‘noisiness’ of trace data, e) privacy, and f) systematic confounds, referred to as algorithmic bias (see Alexander et al., 2020 for a discussion). Since personality assessment is a clinical decision-based enterprise, concerns about the validity of Machine Learning/AI systems due to lack of transparency and interpretability continue to remain a challenge for the psychological assessment field for the near-term future (see BiBantz et al., 2024; Kuper & Kramer, 2024). Despite these limitations, the current discussion should provide an aspirational framework for the potential application of emergent AI technologies to advances in the field of personality assessment (Boyd et al., 2020; Gondalez, 2021; Iliescu & Greiff, 2019). In a recent AI study, Kim et al. (2024) applied drawings in an analysis of psychological state. Thus, going forward, AI will be both an opportunity and challenge for the field of mental health assessment and for clinicians engaged in personality and projective assessment.

References:

Alexander, L., et al. (2020). Using big data and machine learning in personality measurement: Opportunities and challenges.

European Journal of Personality, 34, 632-648.

Bibantz, S., et al. (2024). The potential of machine learning methods in psychological assessment and test construction. European Journal of Psychological Assessment, 40 (1), 1-4.

Bleidorn, W., & Hopwood, C. J. (2019). Using machine learning to advance personality assessment and theory. Personality and Social Psychology Review, 23(2), 190-203.

Botvinick, M. M. (2022). Realizing the promise of AI: A new calling for cognitive science. Trends in Cognitive Sciences, 26(12), 1013-1014.

Boyd, R. L., et al. (2020). The personality panorama: Conceptualizing personality through big behavioral data. European Journal of Personality, 34 (5), 599-612.

Dwyer, D. B., et al. (2018). Machine learning approaches for clinical psychology and psychiatry. Annual Review of Clinical Psychology, 14 (1), 91-118.

Fan, J., et al. (2023). How well can an AI Chatbot infer personality? Examining psychometric properties of machine-inferred personality scores. Journal of Applied Psychology, 108 (8), 1277-1299.

Fokkema, M., et al. (2022). Machine learning and prediction in psychological assessment. European Journal of Psychological Assessment, 38(3), 165-175.

Gado, S., et al. (2022). Artificial intelligence in psychology: How can we enable psychology students to accept and use artificial intelligence? Psychology Learning & Teaching, 21(1), 37-56.

Gondalez, O. (2021). Psychometric and machine learning approaches for diagnostic assessment and tests of individual classification.

Psychological Methods, 26 (2), 236-254.

Hernandez, I., & Nie, W. (2023). The AI-IP: Minimizing the guesswork of personality scale item development through artificial intelligence. Personnel Psychology, 76, 1011-1035.

Hinds, J., & Joinson, A. N. (2024). Digital data and personality: A systematic review and meta-analysis of human perception and computer prediction. Psychological Bulletin, in press.

Iliescu, D., & Greiff, S. (2019). The impact of technology on psychological testing in practice and policy. European Journal of Psychological Assessment, 35(2), 151-155.

Iliescu, D., et al. (2022). Editorial: Artificial intelligence, machine learning, and other demons. European Journal of Psychological Assessment, 38(3), 163-164.

Jordan, M. I., & Mitchell, T.M. (2015). Machine learning: Trends, perspectives, and prospects. Science, 349, 255-260.

Kim, S., et al. (2024). Exploring AI approach to art therapy assessment: A case study on the classification and estimation of psychological state based on a drawing. New Ideas in Psychology, 73, 1-10.

Kuper, A., & Kramer, N. (2024). Psychological traits and appropriate reliance: Factors shaping trust in AI. International Journal of Human-Computer Interaction, in press.

Liou, G., et al. (2022). A psychometric view of technology-based assessments. International Journal of Testing, 22(3), 216-242. Maurya, R.K., et al. (2024). Assessing the use of Chat GPT as a psychoeducational tool for mental health practice. Counselling &

Psychotherapy Research, in press.

Murphy, K.P. (2022). Probabilistic machine learning: An introduction. MIT Press.

O’Conno, C. (2024). Public perspectives on AI diagnosis of mental illness. General Psychiatry, 37(3), 1-4.

Piotrowski, C. (2025). Contemporary AI research: Under-studied areas of scientific investigation. North American Journal of Psychology, 27(1), in press.

Seizer, L., et al. (2024). A primer on sampling rates of ambulatory assessments. Psychological Methods, in press.

Stachl, C., et al. (2020). Predicting personality from patterns of behavior collected with smartphones. Proceedings of the National Academy of Sciences, 117(30), 17680-17687.

Tay, L., et al. (2020). Psychometric and validity issues in machine learning approaches to personality assessment: A focus on social media text mining. European Journal of Personality, 34, 826-844.

Tay, L., et al. (2022). A conceptual framework for investigating and mitigating machine-learning measurement bias (MLMB) in psychological assessment. Advances in Methods and Practices in Psychological Science, 5(1), 1-30.

Zhou, S., et al. (2022). Application of artificial intelligence on psychological interventions and diagnosis. Frontiers in Psychiatry, 13, Article 811665.

Chris Piotrowski, PhD

Senior Editor

University of West Florida, USA Email: piotrowskichris@hotmail.com