Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
This study investigates the intersection of sensory perception and advertising by introducing the Sensory Ad dataset and defining sensation classification tasks (SenseClass) to benchmark large language models (LLMs) and multi-modal language models (MLLMs). The authors propose SenseScore, an automated metric for evaluating sensation evocation, which aligns closely with human assessments, and introduce SAGA, a multi-agent framework designed to enhance the alignment of messages with images, sensory evocation, and persuasive effectiveness. The findings establish a novel foundation for creating and evaluating sensory-aware advertisements, highlighting the potential for AI to enhance persuasive communication through sensory engagement.
Sensory ads can significantly boost persuasive impact by leveraging AI to evoke human experiences more effectively than traditional methods.
Sensory advertising evokes human senses through visual cues, enabling audiences to mentally simulate experiences and increasing persuasive impact. Despite the recent increase in using AI in generating and understanding creative and persuasive content, how advertisements visually evoke sensations remains largely unexplored. In this work, we introduce the first study of understanding, evaluating, and generating sensory ads. We introduce the Sensory Ad dataset, and define sensation classification tasks (SenseClass) to benchmark LLMs and MLLMs. We further propose SenseScore, an automated evaluation metric for sensation evocation achieving strong agreement with human judgments. Finally, we introduce the Sensory Ad Generation (SenseGen) task and propose SAGA, a multi-agent framework that improves message image alignment, sensory evocation, and persuasion. Our work establishes a foundation for sensory-aware visual persuasion.