# The Bots of Persuasion: Examining How Conversational Agents' Linguistic Expressions of Personality Affect User Perceptions and Decisions

arXiv: https://arxiv.org/abs/2602.17185 · HTML: https://mlsanity.com/paper/2602.17185/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 144 references that are in the map.
- First posted on arXiv 19 Feb 2026.

## Builds on (most cited first, 19 of 19)

- [A Prompt Pattern Catalog to Enhance Prompt Engineering with ChatGPT](https://mlsanity.com/paper/2302.11382/) (2023)
- [Persuasion for Good: Towards a Personalized Persuasive Dialogue System for Social Good](https://mlsanity.com/paper/1906.06725/) (2019)
- [AI Deception: A Survey of Examples, Risks, and Potential Solutions](https://mlsanity.com/paper/2308.14752/) (2023)
- [Generative Language Models and Automated Influence Operations: Emerging Threats and Potential Mitigations](https://mlsanity.com/paper/2301.04246/) (2023)
- [The Programmer's Assistant: Conversational Interaction with a Large Language Model for Software Development](https://mlsanity.com/paper/2302.07080/) (2023)
- [Human Feedback is not Gold Standard](https://mlsanity.com/paper/2309.16349/) (2023)
- ["I'm Not Sure, But...": Examining the Impact of Large Language Models' Uncertainty Expression on User Reliance and Trust](https://mlsanity.com/paper/2405.00623/) (2024)
- [Artificial Influence: An Analysis Of AI-Driven Persuasion](https://mlsanity.com/paper/2303.08721/) (2023)
- [Persuasion with Large Language Models: A Survey of Empirical Evidence, Study Methodologies, and Ethical Implications](https://mlsanity.com/paper/2411.06837/) (2024)
- [Putting GPT-4o to the Sword: A Comprehensive Evaluation of Language, Vision, Speech, and Multimodal Proficiency](https://mlsanity.com/paper/2407.09519/) (2024)
- [Effects of Persuasive Dialogues: Testing Bot Identities and Inquiry Strategies](https://mlsanity.com/paper/2001.04564/) (2020)
- [Sentiment Analysis: Automatically Detecting Valence, Emotions, and Other Affectual States from Text](https://mlsanity.com/paper/2005.11882/) (2020)
- [If I Hear You Correctly: Building and Evaluating Interview Chatbots with Active Listening Skills](https://mlsanity.com/paper/2002.01862/) (2020)
- [Computers as Bad Social Actors: Dark Patterns and Anti-Patterns in Interfaces that Act Socially](https://mlsanity.com/paper/2302.04720/) (2023)
- [Dark Patterns at Scale: Findings from a Crawl of 11K Shopping Websites](https://mlsanity.com/paper/1907.07032/) (2019)
- [Maximizing Stylistic Control and Semantic Accuracy in NLG: Personality Variation and Discourse Contrast](https://mlsanity.com/paper/1907.09527/) (2019)
- [Appropriate Fairness Perceptions? On the Effectiveness of Explanations in Enabling People to Assess the Fairness of Automated Decision Systems](https://mlsanity.com/paper/2108.06500/) (2021)
- [People over trust AI-generated medical responses and view them to be as valid as doctors, despite low accuracy](https://mlsanity.com/paper/2408.15266/) (2024)
- [Deceptive AI systems that give explanations are more convincing than honest AI systems and can amplify belief in misinformation](https://mlsanity.com/paper/2408.00024/) (2024)

## Built on by (most cited first, 2 of 2)

- [Annie, Are You Okay? How Style- and Context-Based Personalization Shape AI-Assisted Decision-Making](https://mlsanity.com/paper/2609.24644/) (2026)
- [Deflecting the Value Compass: Interacting with Large Language Models Temporarily Shifts Human Value Priorities Toward Personal Focus](https://mlsanity.com/paper/2609.25586/) (2026)

## Abstract (arXiv)

Large Language Model-powered conversational agents (CAs) are increasingly capable of projecting sophisticated personalities through language, but how these projections affect users is unclear. We thus examine how CA personalities expressed linguistically affect user decisions and perceptions in the context of charitable giving. In a crowdsourced study, 360 participants interacted with one of eight CAs, each projecting a personality composed of three linguistic aspects: attitude (optimistic/pessimistic), authority (authoritative/submissive), and reasoning (emotional/rational). While the CA's composite personality did not affect participants' decisions, it did affect their perceptions and emotional responses. Particularly, participants interacting with pessimistic CAs felt lower emotional state and lower affinity towards the cause, perceived the CA as less trustworthy and less competent, and yet tended to donate more toward the charity. Perceptions of trust, competence, and situational empathy significantly predicted donation decisions. Our findings emphasize the risks CAs pose as instruments of manipulation, subtly influencing user perceptions and decisions.