AI-based personality prediction for human well-being from text data: a systematic review

This study introduces a novel method for predicting the Big Five personality traits through the analysis of speech samples, advancing the field of computational personality assessment. We collected data from 2045 participants who completed a self-reported Big Five personality questionnaire and provided free-form speech samples by introducing themselves without constraints on content. Using pre-trained convolutional neural networks and transformer-based models, we extracted embeddings representing both acoustic features (e.g., tone, pitch, rhythm) and linguistic content from the speech samples. These embeddings were combined and input into gradient boosted tree models to predict personality traits. Our results indicate that personality traits can be effectively predicted from speech, with correlation coefficients between predicted scores and self-reported scores ranging from 0.26 (extraversion) to 0.39 (neuroticism), and from 0.39 to 0.60 for disattenuated correlations. Intraclass correlations show moderate to high consistency in our model’s predictions. This approach captures the subtle ways in which personality traits are expressed through both how people speak and what they say. Our findings underscore the potential of voice-based assessments as a complementary tool in psychological research, providing new insights into the connection between speech and personality.

show abstract

Reconstructive psychological assessment (RPA) applied to the analysis of digital behavioral residues in forensic contexts

Ceballos-Espinoza

2024

JCP

View full text Add to dashboard Cite

Purpose This paper aims to explore advances in indirect personality assessment, with emphasis on the psychology of digital behavior based on the analysis of new technological devices and platforms for interpersonal relationships, identifying – along the way – those findings that may be useful to carry out a reconstructive psychological assessment (RPA) of applicability in the legal context. Design/methodology/approach Different fields of knowledge are explored, transferring the findings to the field of psychology of digital behavior, analyzing the publications that report findings on the analysis of new technological devices and platforms for interpersonal relationships and identifying – along the way – those findings that may result useful to carry out an RPA of applicability in the legal context. Findings The application of RPA represents a significant advance in the integration of criminal psychology and forensic technology in legal contexts, opening new fields of action for forensic psychology. Originality/value The article has transferred advances in computer science to the field of forensic psychology, with emphasis on the relevance of RPA (from the analysis of digital behavioral residues) in the interpretation of behavioral evidence for the indirect evaluation of the personality and within the judicial context (when the victim and/or accused are not included).

show abstract

AI-based personality prediction for human well-being from text data: a systematic review

Cited by 4 publications

References 87 publications

Detecting Big-5 Personality Dimensions from Text Based on Large Language Models

Detecting Big-5 Personality Dimensions from Text Based on Large Language Models

Speech-based personality prediction using deep learning with acoustic and linguistic embeddings

Reconstructive psychological assessment (RPA) applied to the analysis of digital behavioral residues in forensic contexts

Contact Info

Product

Resources

About