Developing a Personality Model for Speech-based Conversational Agents Using the Psycholexical Approach

Abstract

We present the first systematic analysis of personality dimensions developed specifically to describe the personality of speech-based conversational agents. Following the psycholexical approach from psychology, we first report on a new multi-method approach to collect potentially descriptive adjectives from 1) a free description task in an online survey (228 unique descriptors), 2) an interaction task in the lab (176 unique descriptors), and 3) a text analysis of 30,000 online reviews of conversational agents (Alexa, Google Assistant, Cortana) (383 unique descriptors). We aggregate the results into a set of 349 adjectives, which are then rated by 744 people in an online survey. A factor analysis reveals that the commonly used Big Five model for human personality does not adequately describe agent personality. As an initial step to developing a personality model, we propose alternative dimensions and discuss implications for the design of agent personalities, personality-aware personalisation, and future research.

14 pages, 2 figures, 3 tables, CHI'20

References in corpus (3)

• What Makes a Good Conversation? Challenges in Designing Truly Conversational Agents
• Mapping Perceptions of Humanness in Speech-Based Intelligent Personal Assistant Interaction
• Latent Human Traits in the Language of Social Media: An Open-Vocabulary Approach

Cited by in corpus (8)

• Eliciting and Analysing Users' Envisioned Dialogues with Perfect Voice Assistants
• Leveraging Large Language Models to Power Chatbots for Collecting User Self-Reported Data
• What Do We See in Them? Identifying Dimensions of Partner Models for Speech Interfaces Using a Psycholexical Approach
• Like My Aunt Dorothy: Effects of Conversational Styles on Perceptions, Acceptance and Metaphorical Descriptions of Voice Assistants during Later Adulthood
• Legal Obligation and Ethical Best Practice: Towards Meaningful Verbal Consent for Voice Assistants
• LLM-Mediated Domain-Specific Voice Agents: The Case of TextileBot
• Giving Robots a Voice: Human-in-the-Loop Voice Creation and open-ended Labeling
• Talk to the Wall: The Role of Speech Interaction in Collaborative Visual Analytics