基于抖音数据的地铁运营舆情主题识别研究
Research on Topic Identification of Metro Operation Public Opinion Based on Douyin Data
DOI: 10.12677/sa.2026.154066, PDF,   
作者: 张诗怡:同济大学经济与管理学院,上海
关键词: 地铁运营舆情分析主题建模BERTopic抖音Subway Operation Public Opinion Analysis Topic Modeling BERTopic Douyin
摘要: 近年来,短视频平台已成为公众表达意见的重要渠道,聚焦短视频中关于地铁运营管理的讨论,从中挖掘出网友对地铁运营管理的意见和建议,对于提升地铁运营管理水平具有重要意义。本研究以抖音平台为数据源,爬取2018年至2025年间地铁运营相关视频1842条,采用BERTopic主题聚类模型对视频描述文本进行主题建模,识别出24个语义区分度较高的初始主题,并参考国家标准将其归纳为8个大类构成的多层次舆情主题体系。分析表明,公众讨论呈现出从基础服务评价向社会价值认知延伸的特征,既关注安全事故、设备故障、基准票价等运营核心议题,也涉及无障碍服务、智能化运营、人文化服务等人文与社会价值层面,乘客行为主题的识别进一步揭示了地铁空间中个体行为与制度管理的深层互动。本研究构建的主题体系具有多维度、场景化、体验导向的特点,能够系统反映公众对地铁服务的关注焦点与价值诉求,为地铁运营部门开展精细化服务改善、舆情监测预警与公众沟通策略制定提供了清晰的结构化框架与决策依据。
Abstract: In recent years, short video platforms have become an important channel for public opinion expression. Focusing on discussions related to subway operations and management within these platforms, and extracting opinions and suggestions from netizens, is of significant importance for improving the level of subway operation and management. This study uses Douyin as the data source, collecting 1,842 subway operation-related videos from 2018 to 2025. The BERTopic topic modeling approach is applied to analyze video description texts, identifying 24 initial topics with high semantic discriminability. These topics are further categorized into a multi-level thematic framework comprising eight major categories, based on national standards. The analysis reveals that public discussions exhibit a shift from basic service evaluation to social value recognition, covering not only core operational issues such as safety incidents, equipment failures, and fare mechanisms, but also humanistic and social dimensions including barrier-free services, intelligent operations, and cultural expression. The identification of passenger behavior topics further uncovers the deep interaction between individual conduct and institutional management within the subway space. The thematic framework constructed in this study is characterized by multidimensionality, contextualization, and an experience-oriented approach. It systematically reflects the public’s focal points of concern and value demands regarding subway services, providing a clear structured framework and decision-making basis for subway operators to implement refined service improvements, conduct public opinion monitoring and early warning, and develop communication strategies with the public.
文章引用:张诗怡. 基于抖音数据的地铁运营舆情主题识别研究[J]. 统计学与应用, 2026, 15(4): 1-12. https://doi.org/10.12677/sa.2026.154066

参考文献

[1] Guo, Y., Tang, Z. and Guo, J. (2020) Could a Smart City Ameliorate Urban Traffic Congestion? A Quasi-Natural Experiment Based on a Smart City Pilot Program in China. Sustainability, 12, Article 2291. [Google Scholar] [CrossRef
[2] Yang, J., Chen, S., Qin, P., Lu, F. and Liu, A.A. (2018) The Effect of Subway Expansions on Vehicle Congestion: Evidence from Beijing. Journal of Environmental Economics and Management, 88, 114-133. [Google Scholar] [CrossRef
[3] Zhang, J., Xu, X., Hong, L., Wang, S. and Fei, Q. (2011) Networked Analysis of the Shanghai Subway Network, in China. Physica A: Statistical Mechanics and Its Applications, 390, 4562-4570. [Google Scholar] [CrossRef
[4] Deng, Y., Zhang, Y., Yuan, Z., Li, R.Y.M. and Gu, T. (2023) Analyzing Subway Operation Accidents Causations: Apriori Algorithm and Network Approaches. International Journal of Environmental Research and Public Health, 20, Article 3386. [Google Scholar] [CrossRef] [PubMed]
[5] 谭启生. 公共交通购票支付的便利化研究——以广州地铁为例[D]: [硕士学位论文]. 广州: 广东财经大学, 2022.
[6] 赵晓利. 基于用户空间体验的地铁导向标识系统设计研究[D]: [硕士学位论文]. 济南: 山东大学, 2018.
[7] Wu, M., Long, R., Chen, F., Chen, H., Bai, Y., Cheng, K., et al. (2023) Spatio-Temporal Difference Analysis in Climate Change Topics and Sentiment Orientation: Based on LDA and BiLSTM Model. Resources, Conservation and Recycling, 188, Article 106697. [Google Scholar] [CrossRef
[8] Hu, H., Ge, Y. and Hou, D. (2014) Using Web Crawler Technology for Geo-Events Analysis: A Case Study of the Huangyan Island Incident. Sustainability, 6, 1896-1912. [Google Scholar] [CrossRef
[9] Gao, N., Touran, A., Wang, Q. and Beauchamp, N. (2024) Construction Risk Identification Using a Multi-Sentence Context-Aware Method. Automation in Construction, 164, Article 105466. [Google Scholar] [CrossRef
[10] Li, S., You, M., Li, D. and Liu, J. (2022) Identifying Coal Mine Safety Production Risk Factors by Employing Text Mining and Bayesian Network Techniques. Process Safety and Environmental Protection, 162, 1067-1081. [Google Scholar] [CrossRef
[11] Wang, Y., Li, H. and Wu, Z. (2019) Attitude of the Chinese Public toward Off-Site Construction: A Text Mining Study. Journal of Cleaner Production, 238, Article 117926. [Google Scholar] [CrossRef
[12] Estévez-Ortiz, F.J., García-Jiménez, A. and Glösekötter, P. (2016) An Application of People’s Sentiment from Social Media to Smart Cities. El Profesional de la Información, 25, 851-858. [Google Scholar] [CrossRef
[13] Ghosh, S., Chen, Y. and Dou, W. (2024) Railroad Safety: A Systematic Analysis of Twitter Data. Case Studies on Transport Policy, 15, Article 101154. [Google Scholar] [CrossRef
[14] 刘洋, 柳卓心, 金昊, 等. 基于BERTopic模型的用户层次化需求及动机分析——以抖音平台为例[J]. 情报杂志, 2023, 42(12): 159-167.
[15] 沈洪洲, 朱佳, 黄仕靖, 等. 应急知识短视频传播效果研究: 基于不同发布端类型的分析[J]. 情报理论与实践, 2024, 47(11): 101-110.
[16] Anderson, M.L. (2014) Subways, Strikes, and Slowdowns: The Impacts of Public Transit on Traffic Congestion. American Economic Review, 104, 2763-2796. [Google Scholar] [CrossRef
[17] Reddy, A.V., Lu, A. and Wang, T. (2010) Subway Productivity, Profitability, and Performance: A Tale of Five Cities. Transportation Research Record: Journal of the Transportation Research Board, 2143, 48-58. [Google Scholar] [CrossRef
[18] Gallo, M. (2018) The Impact of Urban Transit Systems on Property Values: A Model and Some Evidences from the City of Naples. Journal of Advanced Transportation, 2018, 1-22. [Google Scholar] [CrossRef
[19] He, D., Sun, G., Li, L. and Webster, C. (2024) New Metro and Housing Price and Rent Premiums: A Natural Experiment in China. Urban Studies, 61, 1371-1392. [Google Scholar] [CrossRef
[20] Li, S., Chen, L. and Zhao, P. (2019) The Impact of Metro Services on Housing Prices: A Case Study from Beijing. Transportation, 46, 1291-1317. [Google Scholar] [CrossRef
[21] Xu, T., Zhang, M. and Aditjandra, P.T. (2016) The Impact of Urban Rail Transit on Commercial Property Value: New Evidence from Wuhan, China. Transportation Research Part A: Policy and Practice, 91, 223-235. [Google Scholar] [CrossRef
[22] Li, W., Sun, B., Yin, C., Zhang, T. and Liu, Q. (2018) Does Metro Proximity Promote Happiness? Evidence from Shanghai. Journal of Transport and Land Use, 11, 1271-1285. [Google Scholar] [CrossRef
[23] Li, K., Yuan, W. and Li, J. (2022) Causal Association between Metro Transits and Air Quality: China’s Evidence. Environmental Science and Pollution Research, 29, 70435-70447. [Google Scholar] [CrossRef] [PubMed]
[24] Sun, C., Zhang, W., Luo, Y. and Xu, Y. (2019) The Improvement and Substitution Effect of Transportation Infrastructure on Air Quality: An Empirical Evidence from China’s Rail Transit Construction. Energy Policy, 129, 949-957. [Google Scholar] [CrossRef
[25] Li, Q., Song, L., List, G.F., Deng, Y., Zhou, Z. and Liu, P. (2017) A New Approach to Understand Metro Operation Safety by Exploring Metro Operation Hazard Network (MOHN). Safety Science, 93, 50-61. [Google Scholar] [CrossRef
[26] Li, Z., Zhang, S., Meng, Q. and Hu, X. (2021) Barriers to the Development of Prefabricated Buildings in China: A News Coverage Analysis. Engineering, Construction and Architectural Management, 28, 2884-2903. [Google Scholar] [CrossRef
[27] Tang, L., Zhang, Y., Dai, F., Yoon, Y., Song, Y. and Sharma, R.S. (2017) Social Media Data Analytics for the U.S. Construction Industry: Preliminary Study on Twitter. Journal of Management in Engineering, 33, Article 04017038. [Google Scholar] [CrossRef
[28] Hong, L., Fu, C., Wu, J. and Frias-Martinez, V. (2018) Information Needs and Communication Gaps between Citizens and Local Governments Online during Natural Disasters. Information Systems Frontiers, 20, 1027-1039. [Google Scholar] [CrossRef
[29] Xue, J., Shen, G.Q., Li, Y., Wang, J. and Zafar, I. (2020) Dynamic Stakeholder-Associated Topic Modeling on Public Concerns in Megainfrastructure Projects: Case of Hong Kong-Zhuhai-Macao Bridge. Journal of Management in Engineering, 36, Article 04020078. [Google Scholar] [CrossRef
[30] Tang, L., Griffith, L., Stevens, M. and Hardie, M. (2020) Social Media Analytics in the Construction Industry Comparison Study between China and the United States. Engineering, Construction and Architectural Management, 27, 1877-1889. [Google Scholar] [CrossRef
[31] 翟羽佳, 马柏玉, 陈晓灿. 新冠疫苗信息扩散的共振与联动效应——基于抖音与微博的对比研究[J]. 情报科学, 2023, 41(12): 127-135.
[32] 於世为, 郭迎迎, 陆永香, 等. “拉闸限电”事件原因和影响解析:公众评论大数据驱动视角[J]. 工程管理科技前沿, 2024, 43(1): 30-38.