The impact of social media comments on the sales of domestic new energy vehicles – a case study of byd

Weiyan Yang; Hongyan Li; Wei Yu; Weicong Yin; Yue Lin; Qingqing Chen

doi:10.63313/ESW.9004

Authors

Weiyan Yang Department of International Business, Zhejiang Yuexiu University of Foreign Languages, Zhejiang, China Author
Hongyan Li Department of International Business, Zhejiang Yuexiu University of Foreign Languages, Zhejiang, China Author
Wei Yu Department of International Business, Zhejiang Yuexiu University of Foreign Languages, Zhejiang, China Author
Weicong Yin Department of International Business, Zhejiang Yuexiu University of Foreign Languages, Zhejiang, China Author
Yue Lin Department of International Business, Zhejiang Yuexiu University of Foreign Languages, Zhejiang, China Author
Qingqing Chen Department of International Business, Zhejiang Yuexiu University of Foreign Languages, Zhejiang, China Author

DOI:

https://doi.org/10.63313/ESW.9004

Keywords:

Social Media Comments, New Energy Vehicles, Sales Impact, Text Mining, BYD

Abstract

With the rapid development of information technology, social media has become an important platform for people to obtain information and exchange views. In the new energy vehicle (NEV) market, consumers' decision-making process is in-creasingly influenced by social media comments. This study aims to explore how user comments on social media affect the sales of BYD, China's domestic new en-ergy vehicle brand. By collecting and analyzing the comment data of BYD cars on relevant social media platforms, combined with sales data, text mining technology is used to reveal the relationship between social media comments and sales. The research shows that by using the Latent Dirichlet Allocation (LDA) model to ex-tract the main topics in reviews and comparing them with the sales data of BYD's new energy vehicles, it is found that there is a positive correlation between spe-cific review topics and sales. For example, keywords such as "to work", "power" and "space" have a strong positive correlation with sales in the comment theme, indicating that the theme of these comments is more in line with the consumer demand of the new energy vehicle market, reflecting the concerns and interest points of consumers, and can help car companies develop more accurate market-ing strategies.

References

[1] Li, Yuhui. (2019). Text Mining Analysis of New Energy Vehicles in China. Un-published master’s thesis, Guangxi Normal University.

[2] Chen, L. (2023). Research on Influencing Factors of New Energy Vehicle Sales Based on Multiple Linear Regression. Statistics and Application, 12(1), 17-24. DOI: 10.12677/SA.2023.121003

[3] Xu, L. Y. (2015). Economic evaluation of the investment in new energy vehicles in China: A case study of Beijing City. Master’s thesis, Beijing Jiaotong University.

[4] Chen, Q., Deng, H. Y., & Zhang, R. S. (2019). New energy vehicle policy and situ-ation analy-sis based on LDA thematic model. Journal of Guangzhou University (Natural Science Edi-tion), 18(5), 34.

[5] Wang, K. Q., & Liu, C. M. (2022). Product design improvement based on im-portance per-formance competitor analysis of online reviews. Journal of Computer Integrated Manu-facturing Systems, 28(5), 1496-1506. DOI: 10.13196/j.cims.2022.05.020

[6] Tanțău, A., & Gavrilescu, I. (2019). Key anxiety factors for buying an electric ve-hicle. Management & Marketing. Challenges for the Knowledge Society, 14(2).

[7] Zhao, Z., & Cai, W. (2010). Localization Problem of Faulty Links Based on Sim-ple Network Tomography. Computer Science, 37(1), 108-110. DOI: 10.3969/j.issn.1002-137X.2010.01.025

[8] Shi, W., Wang, H. W., & He, S. Y. (2013). Sentiment analysis of Chinese online reviews based on semantics. Journal of the China Society for Scientific and Tech-nical Information, 32(8), 8. DOI: 10.3772/j.issn.1000-0135.2013.08.009

[9] Yang, B., Cao, Z., Guo, G., Liu, S., & Shen, B. (2022). Research on prediction method of flank wear state of milling cutter based on convolutional neural network. Tool Technology, (056-005).

[10] Jabbari, P., Khaloei, M. and MacKenzie, D. (2019) Estimating Potential Demand for Long-Distance Electric Vehicle Travel in Washington State. 98th Annual Meet-ing of the Transportation Research Board, Washington DC, 13-17 January 2019, 1-7.

[11] Alaoui, S. S., Farhaoui, Y., & Aksasse, B. (2022). Hate Speech Detection Using Text Mining and Machine Learning. International Journal of Decision Support Sys-tem Technology, 14(1).

[12] Peng, G., & Yuefen, W. (2016). Identifying Optimal Topic Numbers from Sci-Tech Infor-mation with LDA Model. Journal of Modern Information Technology, 32(9), 42-50. DOI: 10.11925/infotech.1003-3513.2016.09.05

[13] Yu, M. Y., & Shen, B. (2023). Analysis of Sales of New Energy Vehicles in the Changing In-ternational Situation–Composite Forecasting Model Based on Unex-pected Factors. China Journal of Commerce, 12, 164-168. DOI: 10.19699/j.cnki.issn2096-0298.2023.12.164

[14] Chen, Y. P. (2023). Research on the relationship between social media com-ments and the sales volume of new energy passenger cars [D]. Northern National University.