Work

Research on the Evolution of Online User Reviews of New Energy Vehicles in China Based on LDA

Year: 2025

Type: article

Abstract: To achieve China’s carbon peak and carbon neutrality goals, it is essential to increase the market penetration of New Energy Vehicles (NEVs) and understand consumer attitudes. Based on a big data set of over 20,000 online user reviews, this study employs the Latent Dirichlet Allocation (LDA) model to extract themes, popular brands, and focal points across different time windows. The research constructs a data-driven threshold filtering mechanism that integrates topic probability, frequency, keyword weight, and cross-temporal topic similarity to quantify consumer reviews, enabling an in-depth analysis of the dynamic evolution of attitudes in the NEV market. The findings reveal a dual shift in consumer sentiment: first, a transition in focus from basic configurations and aesthetics toward quality experience; and second, a shift in purchasing decisions toward a socially driven model dominated by word-of-mouth and family collaboration.

Source: World Electric Vehicle Journal

DOI: 10.3390/wevj17010021

Authors: Su He, Bo Xue, Dejiang Luo

Institutions: Sichuan Post and Telecommunications College, China Mobile (China), Chengdu University of Technology

Language: English

Topic: Electric Vehicles and Infrastructure

Subfield: Electrical and Electronic Engineering

Field: Engineering

Domain: Physical Sciences

SDGs: Affordable and clean energy, Climate action

Open Access status: gold

Estimated APC paid: $1,689