Multimodal analysis of personality traits on videos of self-presentation and induced behavior
| Autor: | Dersu Giritlioğlu, Can Ufuk Ertenli, Emre Mutlu, Burak Mandira, Hamdi Dibeklioglu, Selim Firat Yilmaz, Aslı Gül Kurt, Merve Kiniklioglu, Şeref Can Gürel, Berhan Faruk Akgür |
|---|---|
| Přispěvatelé: | RS: FPN CN 4, Cognition, Giritlioğlu, Dersu, Mandira, Burak, Yılmaz, Selim Fırat, Akgür, Berhan Faruk, Kınıklıoğlu, Merve, Kurt, Aslı Gül, Dibeklioğlu, Hamdi, Yilmaz, Selim Firat |
| Jazyk: | angličtina |
| Rok vydání: | 2021 |
| Předmět: |
Computer science
IMPACT media_common.quotation_subject FEATURES 1ST IMPRESSIONS 03 medical and health sciences 0302 clinical medicine Discriminative model PSYCHOTIC DISORDERS 5-FACTOR MODEL Personality Big five Big Five personality traits media_common Facial expression GENDER-DIFFERENCES Modalities Multimodal fusion Self-presentation business.industry Deep learning Contrast (statistics) Estimation of personality traits MAJOR DEPRESSION BIPOLAR I 030227 psychiatry Human-Computer Interaction Signal Processing Artificial intelligence Induced behavior business 030217 neurology & neurosurgery Cognitive psychology Gesture |
| Zdroj: | Journal on Multimodal User Interfaces, 15(4), 337-358. Springer Verlag Journal on Multimodal User Interfaces |
| ISSN: | 1783-7677 |
| DOI: | 10.1007/s12193-020-00347-7 |
| Popis: | Personality analysis is an important area of research in several fields, including psychology, psychiatry, and neuroscience. With the recent dramatic improvements in machine learning, it has also become a popular research area in computer science. While the current computational methods are able to interpret behavioral cues (e.g., facial expressions, gesture, and voice) to estimate the level of (apparent) personality traits, accessible assessment tools are still substandard for practical use, not to mention the need for fast and accurate methods for such analyses. In this study, we present multimodal deep architectures to estimate the Big Five personality traits from (temporal) audio-visual cues and transcribed speech. Furthermore, for a detailed analysis of personality traits, we have collected a new audio-visual dataset, namely: Self-presentation and Induced Behavior Archive for Personality Analysis (SIAP). In contrast to the available datasets, SIAP introduces recordings of induced behavior in addition to self-presentation (speech) videos. With thorough experiments on SIAP and ChaLearn LAP First Impressions datasets, we systematically assess the reliability of different behavioral modalities and their combined use. Furthermore, we investigate the characteristics and discriminative power of induced behavior for personality analysis, showing that the induced behavior indeed includes signs of personality traits. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full text from SpringerLink