Key points are not available for this paper at this time.
The identification of personality by automatic analysis of conversation has many potential applications in natural language processing, from leader identification in meetings to partner matching on dating websites. We automatically train models of the main five personality dimensions, on a corpus of conversation extracts and personality ratings. Results show that the models perform better than the baseline. Qualitative analysis of the models confirms previous findings linking language and personality, while revealing many new linguistic and prosodic markers. 1
Mairesse et al. (2006) studied this question.