社交媒体在新能源汽车领域的影响力研究——以Bilibili为例
The Influence of Social Media in the New Energy Vehicle Sector—A Case Study of Bilibili
摘要: 数字化浪潮下,社交媒体深刻重塑了消费者的信息获取与决策模式。而新能源汽车作为汽车行业的新兴力量,视频形式的社交媒体对其产生的影响越来越大。本文以视频网站Bilibili和蔚来汽车为研究对象,结合口碑传播理论和情绪传染理论探究视频网站及其平台信息对蔚来汽车销量的影响。本研究使用Python获取2018~2024年蔚来汽车相关视频数据以及视频下32万余条评论数据,结合中国汽车工业协会的销量数据展开分析,探讨社交媒体对汽车行业的影响。实证结果表明:1) 视频累计曝光度(即播放量)、用户互动参与度(即评论量)和情感认同指数(即点赞量)对汽车销量均有显著的正向影响且均为销量的不同滞后期的格兰杰原因,并且用户互动参与度的作用更为突出且持续时间更长;2) 在线评论的正负面情绪值对销量存在显著影响,正面情绪促进销量增长以及负面情绪抑制销量,且正面情绪的促进作用更强;3) 此外,本文借助LDA主题聚类算法对评论内容继续分析,“电池”、“企业”、“技术”等主题受关注度较高且所有主题负面情绪占比较大,其中“体验”、“电池”、“设计”主题的负面情绪值对销量产生了直接的负面影响,其中“体验”主题的负面情绪影响最大。
Abstract: Under the digital transformation, social media has profoundly reshaped consumer information acquisition and decision-making patterns. As an emerging force in the automotive industry, new energy vehicles (NEVs) are increasingly influenced by video-based social media platforms. This study focuses on the video-sharing platform Bilibili and the Chinese electric vehicle manufacturer NIO, integrating word-of-mouth communication theory and emotional contagion theory to investigate how platform-driven content impacts NIO’s sales. Utilizing Python, we collected data from NIO-related videos (2018~2024) and over 320,000 comment entries, combined with sales data from the China Association of Automobile Manufacturers, to analyze the role of social media in the automotive sector. Key empirical findings include: 1) Cumulative video exposure (play counts), user interaction engagement (comment volume), and sentiment affinity indices (like counts) exhibit significant positive effects on sales, with all variables acting as Granger causes of sales across different lag periods. User interaction engagement demonstrates a more pronounced and enduring impact. 2) Sentiment polarity in online comments significantly influences sales: positive emotions drive growth, while negative emotions suppress demand, with positive sentiment exerting a stronger promotional effect. 3) Through LDA topic clustering analysis, high-attention themes such as “battery,” “corporate strategy,” and “technology” were identified. Notably, negative sentiment in “user experience,” “battery,” and “design” topics directly reduced sales, with “user experience” negativity having the largest adverse effect.
文章引用:桂远芬, 钱颖. 社交媒体在新能源汽车领域的影响力研究——以Bilibili为例[J]. 运筹与模糊学, 2025, 15(3): 430-446. https://doi.org/10.12677/orf.2025.153174

参考文献

[1] Chen, X., Wang, Y. and Wei, S. (2023) How Does Social Media Influence Car Sales: The Effects of Firm, User, and Professional-Generated Content. Information Technology and Management, 2023, 1-18.
[2] Qin, M., Qiu, S., Zhao, Y., Zhu, W. and Li, S. (2024) Graphic or Short Video? The Influence Mechanism of UGC Types on Consumers’ Purchase Intention—Take Xiaohongshu as an Example. Electronic Commerce Research and Applications, 65, Article 101402. [Google Scholar] [CrossRef
[3] Gao, J.J. and Ye, H.Y. (2023) The Influence of Internet Word-of-Mouth on Consumers’ Choice of Tourist Destination: Take Consumers in East China on the Little Red Book as an Example. Academic Journal of Business & Management, 5, 145-152.
[4] Shu, Z., Carrasco, R.A., Sánchez-Montañés, M. and García-Miguel, J.P. (2024) A Multi-Criteria Decision Support Model for Restaurant Selection Based on Users’ Demand Level: The Case of Dianping.com. Information Processing & Management, 61, Article 103650. [Google Scholar] [CrossRef
[5] Zheng, Z., Yang, H., Fu, Y., Fu, D., Podobnik, B. and Stanley, H.E. (2018) Factors Influencing Message Dissemination through Social Media. Physical Review E, 97, Article 062306. [Google Scholar] [CrossRef] [PubMed]
[6] Tseng, N., Hung, Y. and Nakano, J. (2023) Granger Causality Tests Based on Reduced Variable Information. Journal of Time Series Analysis, 45, 444-462. [Google Scholar] [CrossRef
[7] Tenriawaru, A.N., Tawaha, A.R.A., Rukka, R., Ridwan, M., Chan, N.V. and Syam, S.H. (2023) Vector Autoregressive (VAR) Method in Analyzing the Effect of Inflation on Food Price Volatility (FPV) in Palopo City, Indonesia. International Journal of Professional Business Review, 8, e01872. [Google Scholar] [CrossRef
[8] Bhovichitra, P. and Shrestha, A. (2022) The Impact of Video Marketing on Social Media Platforms on the Millennial’s Purchasing Intention toward Electric Vehicles. Journal of Economics, Finance and Management Studies, 5, 1-5.
[9] Kumar, S., Singh, V. and Goel, R. (2024) Strategic Forecasting for Electric Vehicle Sales: A Cutting-Edge Holistic Model Leveraging Key Factors and Machine Learning Technique. Transportation in Developing Economies, 10, Article No. 23. [Google Scholar] [CrossRef
[10] Kemala, B.K.L., Surjandari, I. and Puspita, A.N.G. (2024) Forecasting Methods for the Electric Vehicle Ownership: A Literature Review. Procedia Computer Science, 234, 87-95. [Google Scholar] [CrossRef
[11] Abu, N. and Ismail, Z. (2015) Forecasting Sales of New Vehicle with Limited Data Using Bass Diffusion Model and Grey Theory. AIP Conference Proceedings, 1643, 467-475. [Google Scholar] [CrossRef
[12] Domarchi, C. and Cherchi, E. (2023) Electric Vehicle Forecasts: A Review of Models and Methods Including Diffusion and Substitution Effects. Transport Reviews, 43, 1118-1143. [Google Scholar] [CrossRef
[13] Shojaie, A. and Fox, E.B. (2022) Granger Causality: A Review and Recent Advances. Annual Review of Statistics and Its Application, 9, 289-319. [Google Scholar] [CrossRef] [PubMed]
[14] Liu, J., Chen, L., Luo, R. and Zhu, J. (2023) A Combination Model Based on Multi-Angle Feature Extraction and Sentiment Analysis: Application to EVS Sales Forecasting. Expert Systems with Applications, 224, Article ID: 119986. [Google Scholar] [CrossRef
[15] Zhang, M., Xu, H., Ma, N. and Pan, X. (2022) Intelligent Vehicle Sales Prediction Based on Online Public Opinion and Online Search Index. Sustainability, 14, Article 10344. [Google Scholar] [CrossRef
[16] Liu, M., Zhao, Z., et al. (2022) A Novel Large-Scale Electric Vehicle Charging Load Forecasting Method and Its Application on Regional Power Distribution Networks. 2022 4th Asia Energy and Electrical Engineering Symposium (AEEES), Chengdu, 25-28 March 2022, 236-241.
[17] Yakubu, H. and Kwong, C.K. (2021) Forecasting the Importance of Product Attributes Using Online Customer Reviews and Google Trends. Technological Forecasting and Social Change, 171, Article ID: 120983. [Google Scholar] [CrossRef
[18] Liu, X., Ren, P., Lv, X. and Li, S. (2024) Service Experience and Customers’ EWOM Behavior on Social Media Platforms: The Role of Platform Symmetry. International Journal of Hospitality Management, 119, Article ID: 103735. [Google Scholar] [CrossRef
[19] Song, M., Law, R. and Duan, Y. (2022) What Are the Obstacles in the Way to “Avoid Landmines”? Influence of Electronic Word-of-Mouth Dispersion on Order Decision from the Self-Construal Perspective. International Journal of Hospitality Management, 107, Article ID: 103334. [Google Scholar] [CrossRef
[20] Ferrara, E. and Yang, Z. (2015) Measuring Emotional Contagion in Social Media. PLOS ONE, 10, e0142390. [Google Scholar] [CrossRef] [PubMed]