MindMem: Multimodal for Predicting Advertisement Memorability Using LLMs and Deep Learning
Sepehr Asgarian, Qayam Jetha, Jouhyun Jeon

TL;DR
MindMem is a multimodal deep learning model that predicts advertisement memorability by integrating text, visuals, and audio, achieving state-of-the-art results and enabling content optimization through LLM-based simulations.
Contribution
The paper introduces MindMem, a novel multimodal model for predicting ad memorability, and MindMem-ReAd, an LLM-driven content optimization tool, advancing advertising effectiveness.
Findings
Achieved Spearman's correlation of 0.631 on LAMBDA dataset.
Achieved Spearman's correlation of 0.731 on Memento10K dataset.
Up to 74.12% improvement in memorability with MindMem-ReAd.
Abstract
In the competitive landscape of advertising, success hinges on effectively navigating and leveraging complex interactions among consumers, advertisers, and advertisement platforms. These multifaceted interactions compel advertisers to optimize strategies for modeling consumer behavior, enhancing brand recall, and tailoring advertisement content. To address these challenges, we present MindMem, a multimodal predictive model for advertisement memorability. By integrating textual, visual, and auditory data, MindMem achieves state-of-the-art performance, with a Spearman's correlation coefficient of 0.631 on the LAMBDA and 0.731 on the Memento10K dataset, consistently surpassing existing methods. Furthermore, our analysis identified key factors influencing advertisement memorability, such as video pacing, scene complexity, and emotional resonance. Expanding on this, we introduced…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsSentiment Analysis and Opinion Mining · Color perception and design · Advanced Text Analysis Techniques
