Evolution of User Opinions on Smart and Connected Products Based on Multimodal Online Reviews
BI Yawen
QIN Jindong
Abstract：With the rapid development of smart and connected products,the vast volume of user-generated online reviews has become a vital source for understanding user preferences and tracking market demand dynamics.To reveal the evolution of user opinions from high-dimensional,heterogeneous,and temporally structured reviews,this study develops a multimodal analytical model capable of dynamically capturing user needs and opinion evolution to support product iteration and enhancement.Specifically,the study first integrates textual and visual features of online reviews to construct the initial nodes of the review network using spectral clustering.Subsequently,by incorporating the temporal memory structure of long short-term memory(LSTM)networks and a weight-learning mechanism into the DeGroot model,a dynamic DeGroot-LSTM model is introduced to adaptively update influence relationships among nodes and capture the nonlinear dynamics of opinion propagation.By analyzing node opinions and weight matrices,the prediction of user demand and opinion evolution trends across different product features is conducted.A case study on the Echo Dot smart speaker demonstrates that the proposed model achieves the average MSE,MAE,and R2 of 0.003 2,0.027 6,and 0.829 5,respectively,across all features,significantly outperforming the static DeGroot model and the linear Ridge regression model.The findings not only provide data-driven decision support for the optimization of smart and connected products but also offer a novel methodological framework for studying opinion evolution from a multimodal online review perspective.
Keywords：smart and connected productsmultimodal online reviewsopinion evolutionDeGroot modelproduct optimization
Publication Date：2025-12-31
Online Publishing Date：2026-01-16(First online date of this platform, not the publication date of the document)
Pages：14( 77-89,109 )