Advancing Automotive Business Strategy through Multimodal Aspect-Based Sentiment Analysis Using SSLU-GRU and YOLO

Abstract

Sentiment analysis (SA) has become a key tool in understanding consumer feedback in the automotive industry. However, most existing models are limited to unimodal data and fail to capture fine-grained, aspect-level sentiments from multimodal sources such as text, images, and video. Additionally, privacy concerns related to user-generated content remain under-addressed. This study proposes a novel Multimodal Aspect-Based Sentiment Analysis (MASA) framework that integrates textual, visual, and video data for business decision-making in the automotive sector. The framework includes a BERT-based aspect dictionary for extracting domain-specific features, SCV-YOLOv5 for object segmentation in images and videos, and a GRU model enhanced with the Sinu-Sigmoidal Linear Unit (SSLU) activation function for sentiment classification. A K-Anonymity method augmented by Kendall's Tau and Spearman's Rank Correlation is employed to protect user privacy in sentiment data. The framework was evaluated using the MuSe Car dataset, encompassing over 60 car brands and 10,000 data samples per brand. The proposed model achieved 98.94% classification accuracy, outperforming baseline models such as BiLSTM and CNN in terms of Mean Absolute Error (0.14), RMSE (1.01), and F1-score (98.15%). Privacy-preservation tests also showed superior performance, with a 98% privacy-preserving rate and lower information loss than traditional methods. The results demonstrate that integrating multimodal input with deep learning and privacy-aware techniques significantly enhances the accuracy and reliability of sentiment analysis in automotive business contexts. The framework enables better alignment of consumer feedback with strategic decisions such as product development and targeted marketing.