|
|
|
| Research on Evolutionary Topic Map of Internet Public Opinion with Multi-dimensional Feature Fusion |
| Liu Yashu1, Zhang Haitao1,2, Xu Hailing1, Wei Ping1 |
1.School of Management, Jilin University, Changchun 130022
2.The Information Resource Research Center, Jilin University, Changchun 130022 |
|
|
|
|
Abstract Exploring changes in opinions of Internet users in the event of sudden public opinion and grasping the development process of public opinion events hold great significance for exploring the development direction of the events and to do a good job in guiding the network public opinion in the new period. Based on the knowledge map method, this paper constructs a public opinion map of specific public opinion comments and uses the LDA theme method to divide the topic attributes of the entities on the map and extract these topic and time attributes, tracking the evolution of topics in an all-round way with multidimensional feature fusion analysis. The public opinion map constructed in this paper can effectively identify the content of the topic under discussion among Internet users and accurately track the evolution of the topic. The map plays a major role in dynamically tracking the opinions of Internet users and understanding the direction of public opinion events. The development process of public opinion events can be divided into three stages: incubation period, outbreak period, and recession period, according to the discussion scale of netizens. The discussion content at each stage is constantly fluctuating.
|
|
Received: 17 May 2019
|
|
|
|
1 StiloG, VelardiP. Efficient temporal mining of micro-blog texts and its application to event discovery[J]. Data Mining and Knowledge Discovery, 2016, 30(2): 372-402.
2 XieW, ZhuF D, JiangJ, et al. TopicSketch: Real-time bursty topic detection from twitter[J]. IEEE Transactions on Knowledge and Data Engineering, 2016, 28(8): 2216-2229.
3 ChenY, AmiriH, LiZ J, et al. Emerging topic detection for organizations from microblogs[C]// Proceedings of the 36th International ACM SIGIR Conference on Research and Development in Information Retrieval. New York: ACM Press, 2013: 43-52.
4 ChenP X, ZhangN L, LiuT F, et al. Latent tree models for hierarchical topic detection[J]. Artificial Intelligence, 2017, 250: 105-124.
5 HuangB, YangY, MahmoodA, et al. Microblog topic detection based on LDA model and single-pass clustering[C]// Proceedings of the International Conference on Rough Sets and Current Trends in Computing. Heidelberg: Springer, 2012, 7413: 166-171.
6 廖海涵, 王曰芬, 关鹏. 微博舆情传播周期中不同传播者的主题挖掘与观点识别[J]. 图书情报工作, 2018, 62(19): 77-85.
7 唐晓波, 王洪艳. 基于潜在语义分析的微博主题挖掘模型研究[J]. 图书情报工作, 2012, 56(24): 114-119.
8 唐晓波, 肖璐. 基于依存句法分析的微博主题挖掘模型研究[J]. 情报科学, 2015, 33(9): 61-65.
9 丁晟春, 王鹏鹏, 龚思兰. 基于社区发现和关键词共现的网络舆情潜在主题发现研究——以新浪微博魏则西事件为例[J]. 情报科学, 2018, 36(7): 78-84.
10 梁晓贺, 田儒雅, 吴蕾, 等. 基于超网络的微博舆情主题挖掘方法[J]. 情报理论与实践, 2017, 40(10): 100-105.
11 BleiD M, NgA Y, JordanM I. Latent Dirichlet allocation[J]. Journal of Machine Learning Research, 2003, 3: 993-1022.
12 王静茹, 陈震. 基于隐含狄利克雷分布的文本主题提取对比研究[J]. 情报科学, 2018, 36(1): 102-107.
13 张海涛, 刘雅姝, 张枭慧, 等. 基于模块度的话题发现及网民情感波动研究——以新浪微博“中美间贸易摩擦”话题为例[J]. 图书情报工作, 2019, 63(4): 6-14. |
|
|
|
