Grounded Persuasive Language Generation for Automated Marketing

2025-02-24

AI Summary

This paper addresses the challenge of jointly optimizing persuasive appeal and factual consistency in automated real estate marketing copy generation. We propose a three-module “grounded persuasion” framework that synergistically integrates market feature prediction, user preference modeling, and localized, verifiable attribute extraction. Leveraging large language models (LLMs) and structured prompt engineering, the framework generates personalized, fact-anchored property descriptions. Our key contribution lies in unifying user-intent alignment, domain-specific knowledge constraints, and interpretable factual verification—ensuring outputs are both marketing-effective and empirically verifiable. In evaluations with real homebuyer focus groups, our generated property descriptions significantly outperformed those written by human domain experts (p < 0.01). To our knowledge, this is the first study to empirically validate the feasibility of high-fidelity, responsible large-scale automation for real estate marketing.

Technology Category

• Knowledge Representation and Reasoning: Preferences
• Natural Language Processing: Fact-Checking / Misinformation Detection (NLP Focus)
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work
• Search and Retrieval-Augmented AI: Agentic search
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

Abstract

This paper develops an agentic framework that employs large language models (LLMs) to automate the generation of persuasive and grounded marketing content, using real estate listing descriptions as our focal application domain. Our method is designed to align the generated content with user preferences while highlighting useful factual attributes. This agent consists of three key modules: (1) Grounding Module, mimicking expert human behavior to predict marketable features; (2) Personalization Module, aligning content with user preferences; (3) Marketing Module, ensuring factual accuracy and the inclusion of localized features. We conduct systematic human-subject experiments in the domain of real estate marketing, with a focus group of potential house buyers. The results demonstrate that marketing descriptions generated by our approach are preferred over those written by human experts by a clear margin. Our findings suggest a promising LLM-based agentic framework to automate large-scale targeted marketing while ensuring responsible generation using only facts.

Problem

• Automates persuasive marketing content generation
• Aligns content with user preferences
• Ensures factual accuracy in marketing descriptions

Innovation

• LLM-based agentic marketing framework
• Grounded, personalized, and factual modules
• Automated persuasive content generation