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

Abstract 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...

Full description

Saved in:
Bibliographic Details
Main Author: Martin Lukac
Format: Article
Language:English
Published: Nature Portfolio 2024-12-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-024-81047-0
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1832585746811191296
author Martin Lukac
author_facet Martin Lukac
author_sort Martin Lukac
collection DOAJ
description Abstract 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.
format Article
id doaj-art-ec1c59d0a2754f1ebe722d1210f9e8bc
institution Kabale University
issn 2045-2322
language English
publishDate 2024-12-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-ec1c59d0a2754f1ebe722d1210f9e8bc2025-01-26T12:34:56ZengNature PortfolioScientific Reports2045-23222024-12-0114111310.1038/s41598-024-81047-0Speech-based personality prediction using deep learning with acoustic and linguistic embeddingsMartin Lukac0KoiosAbstract 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.https://doi.org/10.1038/s41598-024-81047-0PersonalitySpeechMachine learningPsychological assessmentComputational social science
spellingShingle Martin Lukac
Speech-based personality prediction using deep learning with acoustic and linguistic embeddings
Scientific Reports
Personality
Speech
Machine learning
Psychological assessment
Computational social science
title Speech-based personality prediction using deep learning with acoustic and linguistic embeddings
title_full Speech-based personality prediction using deep learning with acoustic and linguistic embeddings
title_fullStr Speech-based personality prediction using deep learning with acoustic and linguistic embeddings
title_full_unstemmed Speech-based personality prediction using deep learning with acoustic and linguistic embeddings
title_short Speech-based personality prediction using deep learning with acoustic and linguistic embeddings
title_sort speech based personality prediction using deep learning with acoustic and linguistic embeddings
topic Personality
Speech
Machine learning
Psychological assessment
Computational social science
url https://doi.org/10.1038/s41598-024-81047-0
work_keys_str_mv AT martinlukac speechbasedpersonalitypredictionusingdeeplearningwithacousticandlinguisticembeddings