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

arXiv: https://arxiv.org/abs/2003.06186 · HTML: https://mlsanity.com/paper/2003.06186/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Mar 2020.

## Built on by (most cited first, 8 of 8)

- [Leveraging Large Language Models to Power Chatbots for Collecting User Self-Reported Data](https://mlsanity.com/paper/2301.05843/) (2023)
- [Mirages: On Anthropomorphism in Dialogue Systems](https://mlsanity.com/paper/2305.09800/) (2023)
- [CloChat: Understanding How People Customize, Interact, and Experience Personas in Large Language Models](https://mlsanity.com/paper/2402.15265/) (2024)
- [What Do We See in Them? Identifying Dimensions of Partner Models for Speech Interfaces Using a Psycholexical Approach](https://mlsanity.com/paper/2102.02094/) (2021)
- [Do GPT Language Models Suffer From Split Personality Disorder? The Advent Of Substrate-Free Psychometrics](https://mlsanity.com/paper/2408.07377/) (2024)
- [LLM-Mediated Domain-Specific Voice Agents: The Case of TextileBot](https://mlsanity.com/paper/2406.10590/) (2024)
- [Exploring User Acceptance and Concerns toward LLM-powered Conversational Agents in Immersive Extended Reality](https://mlsanity.com/paper/2512.15343/) (2025)
- [Assessing the Applicability of Existing Design Recommendations to AI Companion Design: A Multi-Method Study](https://mlsanity.com/paper/2609.14236/) (2026)

## Abstract (arXiv)

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.