This study investigates public sentiment and thematic concerns regarding electric vehicle (EV) charging infrastructure in China, employing sentiment analysis and topic modeling, to analyze users’ reviews from the TealDrive app and Weibo comments. Utilizing the SnowNLP library, Utilizing the SnowNLP library, a sentiment analysis was conducted to reveal a diverse range of users’ opinions, uncovering prevalent issues and positive aspects of EV charging services. Additionally, the Latent Dirichlet Allocation (LDA) method was employed for topic modeling, identifying five key themes: community-level EV charging infrastructure, green travel and charging stations, public charging infrastructure and equipment, regulations and market dynamics, and global market and battery technology. The findings of the present paper indicate a significant need for improvements in charging infrastructure, enhanced regulatory support, and technological advancements. Limitations of the study include the size of the data set and potential platform bias, pointing to the need for broader future research. These insights are crucial for policymakers and businesses to enhance EV charging services, promoting sustainable transportation and the wider adoption of electric vehicles.
Electric vehicles, Charging infrastructure, Sentiment analysis, LDA model.
Mincong TANG, Jie CAO, Zixiang FAN, Daqing GONG, Gang XUE, "Public Perceptions of EV Charging Infrastructure: A Combined Sentiment Analysis and Topic Modeling Approach", Studies in Informatics and Control, ISSN 1220-1766, vol. 33(2), pp. 59-72, 2024. https://doi.org/10.24846/v33i2y202406
All articles published by Studies in Informatics and Control (SIC) are published in accordance with the terms and conditions of the Creative Commons Attribution License (CC BY-NC-SA 4.0).