Identifying Personality Traits Using Overlap Dynamics in Multiparty Dialogue
This work addresses the challenge of personality trait identification in multiparty dialogue for applications in social computing and human-computer interaction, but it is incremental as it builds on existing speech-based personality research.
The paper tackled the problem of identifying speaker personality traits from multiparty spoken dialogues by analyzing overlap dynamics, finding that features significantly vary for Extraversion and Conscientiousness and that classifiers using these features outperform random guessing for Extraversion and Agreeableness with statistically significant improvements.
Research on human spoken language has shown that speech plays an important role in identifying speaker personality traits. In this work, we propose an approach for identifying speaker personality traits using overlap dynamics in multiparty spoken dialogues. We first define a set of novel features representing the overlap dynamics of each speaker. We then investigate the impact of speaker personality traits on these features using ANOVA tests. We find that features of overlap dynamics significantly vary for speakers with different levels of both Extraversion and Conscientiousness. Finally, we find that classifiers using only overlap dynamics features outperform random guessing in identifying Extraversion and Agreeableness, and that the improvements are statistically significant.