图书情报工作

图书情报工作 >

2025 , Vol. 69 >Issue 11: 101 - 110

DOI: https://doi.org/10.13266/j.issn.0252-3116.2025.11.009

研究论文

融合IP属地信息的网络舆情时空涨落度测度研究

  • 黄微 ,
  • 张晓君 ,
  • 杨佩霖
展开
  • 1 吉林大学商学与管理学院, 长春 130012;
    2 吉林大学教务处, 长春 130012
黄微，教授，博士生导师，E-mail:huangwei@jlu.edu.cn；张晓君，正高级工程师，博士；杨佩霖，博士研究生。

收稿日期: 2024-06-07

  修回日期: 2024-10-12

  网络出版日期: 2025-05-28

基金资助

本文系国家自然科学基金面上项目“重大突发事件网络舆情受众的参与行为标定、轨迹拟合与靶向导控研究”（项目编号：72174072）研究成果之一。

收起

Research on Measuring Spatiotemporal Fluctuation of Network Public Opinion by Integrating IP Territorial Information

  • Huang Wei ,
  • Zhang Xiaojun ,
  • Yang Peilin
Expand
  • 1 School of Business and Management, Jilin University, Changchun 130012;
    2 Academic Affairs Office, Jilin University, Changchun 130012
Huang Wei, professor, PhD, doctoral supervisor, E-mail: huangwei@jlu.edu.cn; Zhang Xiaojun, senior engineer, PhD; Yang Peilin, doctoral candidate.

Received date: 2024-06-07

  Revised date: 2024-10-12

  Online published: 2025-05-28

Supported by

This work is supported by the National Natural Science Foundation of China project, titled “Research on Behavior Calibration, Trajectory Fitting, and Targeted Guidance Control of Online Public Opinion Audience Participation in Major Emergencies” (Grant No. 72174072).

Fold

摘要

[目的/意义] 网络舆情的传播不仅在时间上有暴发风险，在空间上也存在聚集现象。实质性融合时间信息与空间信息，有助于揭示网络舆情的时空演化发展规律，为舆情管控提供更有针对性的时空参考。[方法/过程] 构建网络舆情的时空涨落度数学模型，阐明时空涨落的阶段划分原理。并结合“中国电科员工痛批加班”网络舆情事件的全周期数据，融合IP属地信息，利用多种机器学习模型进行效果对比，选取最优模型XGBoost进行时空涨落度阶段识别训练及验证。[结果/结论] 网络舆情时空涨落度体现了舆情发展的时空特征，同步加入空间数据的演化分析方法，突破了以往仅从时间角度分析舆情演化的局限，能同时有效揭示舆情的时空双维度热议程度，为舆情管控工作提供了新的量化方法参考和监管视角。

关键词： IP属地; 网络舆情; 时空涨落; 机器学习

本文引用格式

黄微 , 张晓君 , 杨佩霖 . 融合IP属地信息的网络舆情时空涨落度测度研究[J]. 图书情报工作, 2025 , 69(11) : 101 -110 . DOI: 10.13266/j.issn.0252-3116.2025.11.009

Abstract

[Purpose/Significance] The spread of network public opinion not only carries the risk of explosion in time, but also exhibits clustering phenomena in space. The substantive integration of time and spatial information is helpful to reveal the spatiotemporal evolution law of network public opinion and provide more targeted spatiotemporal references for public opinion control. [Method/Process] This study constructed a mathematical spatiotemporal fluctuation model for the network public opinion, and clarified its stage division principle. Based on the full cycle data of network public opinion incident of “Employees in China Electronics Technology Group Co. Criticizing Overtime Painfully” and integrating IP territorial information, multiple machine learning models were used for performance comparison. And the optimal model XGBoost was selected for training and validation of spatiotemporal fluctuation stage recognition. [Result/Conclusion] The spatiotemporal fluctuation of network public opinion reflects the spatiotemporal characteristics of public opinion development. The evolutionary analysis method that synchronously incorporates spatial data breaks through the limitations of analyzing public opinion evolution only from a temporal perspective in the past. It can effectively reveal the degree of spatiotemporal discussion, and provide a new quantitative method for public opinion control work and regulatory perspective.

Key words： IP territory; network public opinion; spatiotemporal fluctuation; machine learning

参考文献

[1] 周子明, 高慎波. 高校网络舆情的生成逻辑、风险特点及应对策略研究[J]. 情报科学, 2022, 40(3): 152-158. (ZHOU Z M, GAO S B. Generation logic, risk characteristics and coping strategies of university network public opinion[J]. Information science, 2022, 40(3): 152-158.)
[2] 邢云菲, 王晰巍. 基于时空大数据的社交网络舆情演化图谱研究——以“天和核心舱发射”话题为例[J]. 情报资料工作, 2022, 43(2): 46-55. (XING Y F, WANG X W. Research on evolution map of social network public opinion based on spatiotemporal big data: taking the topic of “the launch of Tianhe core module” as an example[J]. Information and documentation services, 2022, 43(2): 46-55.)
[3] 金哲. 新学科辞海[M]. 成都: 四川人民出版社, 1994: 1922-1923. (JIN Z. New discipline unabridged dictionary[M]. Chengdu: Sichuan People’s Publishing House, 1994: 1922-1923.)
[4] 江秀乐. 系统科学知识词典[M]. 西安: 陕西人民教育出版社, 1991: 304-305. (JIANG X L. Dictionary of systems science knowledge[M]. Xi’an: Shanxi People’s Education Press, 1991: 304-305.)
[5] 郑家亨. 统计大辞典[M]. 北京: 中国统计出版社, 1995: 1382-1383. (ZHENG J H. Statistical dictionary[M]. Beijing: China Statistics Press, 1995: 1382-1383.)
[6] 王越. 系统理论与人工系统设计学[M]. 北京: 北京理工大学出版社, 2019: 48-50. (WANG Y. System theory and artificial system design[M]. Beijing: Beijing Institute of Technology Press, 2019: 48-50.)
[7] 侯俊华. 热力学·统计物理学[M]. 西安: 西安交通大学出版社, 2022: 210-211. (HOU J H. Thermodynamics · Statistical Physics[M]. Xi’an: Xi’an Jiaotong University Press, 2022: 210-211.)
[8] 单斌, 李芳. 基于LDA话题演化研究方法综述[J]. 中文信息学报, 2010, 24(6): 43-49, 68. (SHAN B, LI F. A survey of topic evolution based on LDA[J]. Journal of Chinese information processing, 2010, 24(6): 43-49, 68.)
[9] XIAO Y, ZHANG F, CUI G. Requirement acquisition method of product life cycle based on HLDA hierarchy model under the background of web technology[J]. Journal of physics: conference series, 2021, 1881: 022067
[10] SHEN J, HUANG W, HU Q. PICF-LDA: a topic enhanced LDA with probability incremental correction factor for web API service clustering[J]. Journal of cloud computing, 2022, 11(1): 1-13.
[11] TAN X, ZHUANG M, LU X. An analysis of the emotional evolution of large-scale internet public opinion events based on the BERT-LDA hybrid model[J]. IEEE Access, 2021, 9: 15860-15871.
[12] 马捷, 郝志远. 机器学习视域下融合情感元素的社交网络信息交互度量化分析[J]. 情报学报, 2021, 40(7): 687-696. (MA J, HAO Z Y. Quantitatively analyzing social network information interaction: integrating the emotional elements from machine learnings perspective[J]. Journal of the China Society for Scientific and Technical Information, 2021, 40(7): 687-696.)
[13] 陈涛, 林杰. 基于搜索引擎关注度的网络舆情时空演化比较分析——以谷歌趋势和百度指数比较为例[J]. 情报杂志, 2013, 32(3): 7-10, 16. (CHEN T, LIN J. Comparative analysis of Temporal-Spatial evolution of online public opinion based on search engine attention: cases of Google trends and Baidu index[J]. Journal of intelligence, 2013, 32(3): 7-10, 16.)
[14] MA D, ZHANG C, ZHAO L. An analysis of the evolution of public sentiment and spatio-temporal dynamics regarding building collapse accidents based on Sina Weibo data[J]. ISPRS international journal of geo-information, 2023, 12: 388.
[15] WANG W, ZHU X, LU P. Spatio-temporal evolution of public opinion on urban flooding: case study of the 7.20 Henan extreme flood event[J]. International journal of disaster risk reduction, 2024, 100: 104175.
[16] 陈华, 张煜巍. 企业社会责任负面事件网络舆情演化阶段式建模分析[J]. 中国管理科学, 2023, 31(2): 195-204. (CHEN H, ZHANG Y W. Staged modeling analysis of the evolution of net-mediated public sentiment on corporate social responsibility negative events[J]. Chinese journal of management science, 2023, 31(2): 195-204.)
[17] 兰月新, 曾润喜. 突发事件网络舆情传播规律与预警阶段研究[J]. 情报杂志, 2013, 32(5): 16-19. (LAN Y X, ZENG R X. Research of emergency network public opinion on propagation model and warning phase[J]. Journal of intelligence, 2013, 32(5): 16-19.)
[18] 胡峰. 重大疫情网络舆情演变机理及跨界治理研究——基于“四点四阶段”演化模型[J]. 情报理论与实践, 2020, 43(6): 23-29, 55. (HU F. Research on the evolution of internet public opinion and transboundary governance of major epidemic: based on the “Four Points and Four Stages” evolution model[J]. Information studies: theory & application, 2020, 43(6): 23-29, 55.)
[19] 马旭. 高校突发事件网络舆情传播与演化研究[J]. 情报科学, 2022, 40(12): 120-125. (MA Xu. Research on the dissemination and evolution of network public opinion in university emergencies[J]. Information science, 2022, 40(12): 120-125.)
[20] 刘宇浩, 周剑, 王伟. 中国经济发展方式绿色转型的水平测度、时空演进与收敛特征[J]. 经济纵横, 2024(9): 66-79. (LIU H Y, ZHOU J, WANG W. Green Transformation of Chinese economic growth model: measurement, spatiotemporal evolution, and convergence characteristics[J]. Economic review, 2024(9): 66-79.)
[21] 左文超, 胡北明, 邱雪梅, 等. 消费信心重塑期的旅游消费脆弱性评价及时空演变特征分析[J]. 干旱区资源与环境, 2024, 38(10): 199-208. (ZUO W C, HU B M, QIU X M. Evaluation of tourist consumption vulnerability and characterization of spatiotemporal evolution during the period of consumer confidence remodeling[J]. Journal of arid land resources and environment, 2024, 38(10): 199-208.)
[22] 郭宇星, 孙从建, 陈伟, 等. 黄河中游不同地貌条件下植被干旱时空特征及影响因素[J]. 地理科学, 2024, 44(9): 1676-1683. (GUO Y X, XUN C J, CHEN W. Spatio-temporal characteristics and driving factors of vegetation drought in the middle Yellow River under different geomorphic conditions[J]. Scientia geographica sinica, 2024, 44(9): 1676-1683.)
[23] 姜渭宗, 徐建辉, 赵田. 基于夜间灯光数据的长江流域碳排放时空格局及异质性研究[J]. 长江流域资源与环境, 2024, 33(9): 2004-2017. (JIANG W Z, WU J H, ZHAO T. Spatio-temporal pattern and heterogeneity of carbon emissions based on multi-source nighttime light data in the Yangtze basin[J]. Resources and environment in the Yangtze basin, 2024, 33(9): 2004-2017.)
[24] 连芷萱, 兰月新, 夏一雪, 等. 基于首发信息的微博舆情热度预测模型[J]. 情报科学, 2018, 36(9): 107-114. (LIAN Z X, LAN Y X. The research of micro-blog public opinion popularity forecasting model based on the firstly published information[J]. Information science, 2018, 36(9): 107-114.)
[25] 杨浩. 模型与算法[M]. 北京: 北方交通大学出版社, 2002: 208-212. (YANG H. Models and algorithms[M]. Beijing: Northern Jiaotong University Press, 2002: 208-212.)
[26] 李晨阳, 郑东健. 基于多层次数据处理的NGO-XGBoost大坝变形预测模型及其应用[J]. 水电能源科学, 2023, 41(11): 77-81. (LI C Y, ZHENG D J. Multi-Level data processing-based NGO-XGBoost model for dam deformation prediction[J]. Water resources and power, 2023, 41(11): 77-81.)
[27] 张利斌, 吴宗文. 基于XGBoost机器学习模型的信用评分卡与基于逻辑回归模型的对比[J]. 中南民族大学学报(自然科学版), 2023, 42(6): 846-852. (ZHANG L B, WU Z W. Credit scoring card based on XGBoost machine learning model compared with logistic regression model[J]. Journal of South-Central Minzu University(natural science edition), 2023, 42(6): 846-852.)
[28] 龚德才, 杜宁, 王莉, 等. 基于XGBoost-LME模型的京津冀地区近地面臭氧浓度估算[J]. 环境科学, 2024: 1-16. (GONG D C, DU N, WANG L. Estimation of near-surface ozone concentration in the Beijing-Tianjin-Hebei region based on XGBoost-LME model[J]. Environmental science, 2024: 1-16.)
[29] 冉勇川, 曾军, 张毅. 城市运行工况下纯电动汽车续航里程的SVM模型预测方法的研究[J]. 机械科学与技术, 2024: 1-9. (RAN Y C, ZENG J, ZHANG Y. Research on SVM model prediction method of pure electric vehicle cruising range under urban operating conditions[J]. Mechanical science and technology for aerospace engineering, 2024: 1-9.)
[30] 熊璐伟, 钟晓阳, 李庶林, 等. 基于改进的HHT-SVM微震信号特征提取及分类识别研究[J]. 中国安全生产科学技术, 2023, 19(10): 13-20. (XIONG L W, ZHONG X Y, LI Z L. Research on feature extraction and classification and identification of microseismic signals based on improved HHT-SVM[J]. Journal of safety science and technology, 2023, 19(10): 13-20.)
[31] 李艳艳, 严佳梅, 虞云飞, 等. 基于XGBoost与LR算法的95598重复来电行为研究[J]. 企业科技与发展, 2022, 493(11): 36-38. (LI Y Y, YAN J M, YU Y F. Research on 95598 repeated call behavior based on XGBoost and LR algorithm [J]. Enterprise technology and development, 2022, 493(11): 36-38.)
[32] 刘昱萌, 刘斌. 基于LGB-FFM-LR算法的在线课程评分预测方法研究[J]. 电子测量技术, 2021, 44(16): 1-6. (LIU Y M, LIU B. Prediction methods of online course grading based on LGB-FFM-LR[J]. Electronic measurement technology, 2021, 44(16): 1-6.)
[33] 孙丹, 饶兰香, 施炜利, 等. 基于混合N-Gram模型和XGBoost算法的内部威胁检测方法[J]. 计算机与现代化, 2022, 324(8): 99-105. (SUN D, RAO L X, SHI W L. Insider threat detection based on yybrid N-Gram and XGBoost theory. [J]. Computers and modernization, 2022, 324(8): 99-105.)
[34] 何龙. 深入理解XGBoost高效机器学习算法与进阶[M]. 北京: 机械工业出版社, 2020: 308-309. (HE L. Deeply understand the XGBoost efficient machine learning algorithm and its advanced features[M]. Beijing: Machinery Industry Press, 2020: 308-309.)
Options
文章导航

/

〈 〉