Research on Advertising Effect Evaluation Model and Algorithm Based on Multimodal Data

Abstract

The rapid growth of digital advertising has created a dynamic situation with a wide range of content types and complex customer behavior. The variety of data sources accessible in the age of digital marketing has made assessing the success of advertising efforts a difficult task. This study’s goal is to explore a novel multimodal data-based advertising effect evaluation model and algorithm to offer a thorough examination of digital advertising effectiveness. To collect multi-model data, which include text, audio, video, and user interaction data related to the advertisement, the data were preprocessed to handle stemming, image resizing, and normalization of the obtained multi-model data. Then, the features are extracted using convolution neural networks (CNNs) employed to extract visual features, while bag of words (BoW) is used to analyze audio and text data for emotional patterns. Finally, the extracted features are fused. This study proposed a novel modified crayfish-optimized multimodal long short-term memory (MCFO-MLSTM) to evaluate the effectiveness of the advertisement. The model dynamically adjusts video content and playback mode based on user emotions and behaviors, enhancing engagement and ad effectiveness. The findings show that the suggested approach performs better in terms of consumer satisfaction with tailored advertisements, enhances advertising design, and increases viewer engagement. This research contributes to advancing advertising evaluation techniques by incorporating multimodal data and emotion-driven algorithms.