PVP: An Image Dataset for Personalized Visual Persuasion with Persuasion Strategies, Viewer Characteristics, and Persuasiveness Ratings

2025-05-31

AI Summary

Prior work lacks large-scale datasets linking image persuasiveness to annotator-level psychological traits, hindering the development of personalized visual persuasion systems. Method: We introduce PVP—the first large-scale dataset for this task—comprising 28,454 images, 596 persuasive messages, 9 rhetorical strategies, and multidimensional annotator attributes (age, gender, personality, values) alongside fine-grained persuasiveness ratings from 2,521 annotators. We propose a unified framework integrating strategy-aware modeling, viewer trait embedding, and strategy-conditioned evaluation. Further, we develop a diffusion-based persuasive image generator and a multimodal persuasiveness assessment model, establishing dual-generation-and-evaluation benchmarks. Contribution/Results: Incorporating psychological features improves persuasiveness prediction accuracy by 12.7%; generated images achieve a 19.3% average lift in click-through rate in A/B tests, demonstrating the efficacy of personalized persuasion modeling.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Application Domains: Humanities & Computational Social Science
• Humans and AI: Voting

Application Category

• User Modeling, Personalization and Recommendation: Metrics for user behavior and evaluating success
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web

Abstract

Visual persuasion, which uses visual elements to influence cognition and behaviors, is crucial in fields such as advertising and political communication. With recent advancements in artificial intelligence, there is growing potential to develop persuasive systems that automatically generate persuasive images tailored to individuals. However, a significant bottleneck in this area is the lack of comprehensive datasets that connect the persuasiveness of images with the personal information about those who evaluated the images. To address this gap and facilitate technological advancements in personalized visual persuasion, we release the Personalized Visual Persuasion (PVP) dataset, comprising 28,454 persuasive images across 596 messages and 9 persuasion strategies. Importantly, the PVP dataset provides persuasiveness scores of images evaluated by 2,521 human annotators, along with their demographic and psychological characteristics (personality traits and values). We demonstrate the utility of our dataset by developing a persuasive image generator and an automated evaluator, and establish benchmark baselines. Our experiments reveal that incorporating psychological characteristics enhances the generation and evaluation of persuasive images, providing valuable insights for personalized visual persuasion.

Problem

• Lack of datasets linking image persuasiveness to viewer traits
• Need for personalized AI-generated persuasive visual content
• Absence of benchmarks for evaluating persuasive image effectiveness

Innovation

• PVP dataset links images to viewer traits
• AI generates personalized persuasive images
• Psychological traits improve image persuasiveness