Assessment of Personality Dimensions Across Situations Using Conversational Speech

2025-07-25

AI Summary

This study investigates how situational context—specifically, neutral job interviews versus high-pressure customer interactions—affects perception-based personality assessment from conversational speech. We extract hand-crafted acoustic features (e.g., loudness, intensity, spectral flux) and nonverbal behavioral cues, and compare them against speaker embeddings to build multi-context personality perception models. Results demonstrate strong contextual dependency in perceived personality, challenging the assumption of personality as a static trait. Prediction accuracy for Neuroticism is highest in high-pressure contexts, and hand-crafted acoustic features consistently outperform speaker embeddings across conditions. Moreover, cross-context predictability varies significantly across the Big Five dimensions, revealing the dynamic nature of speech–personality mappings. These findings provide novel empirical evidence and a modeling framework for context-aware personality computing and human–computer interaction.

Technology Category

• Natural Language Processing: Speech
• Cognitive Modeling & Cognitive Systems: Affective Computing
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval

Application Category

• User Modeling, Personalization and Recommendation: Practical large-scale studies of user experience
• Search and Retrieval-Augmented AI: Personalized, context-aware and across-device search
• Security and Privacy: Large-scale security measurements

Abstract

Prior research indicates that users prefer assistive technologies whose personalities align with their own. This has sparked interest in automatic personality perception (APP), which aims to predict an individual's perceived personality traits. Previous studies in APP have treated personalities as static traits, independent of context. However, perceived personalities can vary by context and situation as shown in psychological research. In this study, we investigate the relationship between conversational speech and perceived personality for participants engaged in two work situations (a neutral interview and a stressful client interaction). Our key findings are: 1) perceived personalities differ significantly across interactions, 2) loudness, sound level, and spectral flux features are indicative of perceived extraversion, agreeableness, conscientiousness, and openness in neutral interactions, while neuroticism correlates with these features in stressful contexts, 3) handcrafted acoustic features and non-verbal features outperform speaker embeddings in inference of perceived personality, and 4) stressful interactions are more predictive of neuroticism, aligning with existing psychological research.

Problem

• Assessing dynamic personality traits in different conversational situations
• Identifying speech features linked to perceived personality variations
• Comparing feature effectiveness for personality inference across contexts

Innovation

• Analyzing conversational speech for dynamic personality traits
• Using acoustic features to predict context-dependent personality
• Handcrafted features outperform embeddings in personality inference