Analysis and Modeling of Self-Reported and Observer-Reported Personality Scores from Text and Speech

Automatic personality detection from speech has applications in diverse domains. Most previous efforts to automatically detect personality have aimed to predict either self-reported personality measures or personality labels provided by observers. It is unclear which kind of personality labels are preferable for speech-based personality recognition tasks or whether they are correlated with each other. In this work we aim to understand how self-reported and observer-reported measures of personality relate to each other. We conduct a study of personality ratings by collecting personality judgments from external raters using a corpus of spontaneous speech from speakers with self-reported personality scores. We then proceed to build and compare predictive models of self-reported personality scores and observer-reported personality using acoustic-prosodic and lexical features. Finally, we explore the effect of modality on observer-reported personality judgments, comparing judgments of speech stimuli with judgments of transcribed speech.