|
|
|
| User Role Recognition of Social Media Public Opinion Based on Heterogeneous Hypernetwork Representation Learning from the Perspective of Symbolic Interaction Theory |
| Shen Wang, Sun Ke, Li He, Liu Jiayu |
| School of Business and Management, Jilin University, Changchun 130012 |
|
|
|
|
Abstract The core challenge of social media public opinion analysis lies in its multi-dimensional and heterogeneous information interaction mechanism, making accurate identification of user roles the key to understanding the law of information diffusion and accurate public opinion guidance. To address the current research limitations of overemphasizing high-impact user identification and inadequately integrating semantic information with network topology, this study proposes a user role identification method that integrates symbolic interaction theory and heterogeneous hypernetwork representation learning. Initially, grounded in symbolic interaction theory, we constructed a three-layer heterogeneous hypernetwork model comprising social behavior, information dissemination, and topic semantic layers, to systematically characterize the multi-dimensional interaction patterns of users. Subsequently, heterogeneous hypernetwork representation learning that included a multi-layer graph attention network and a cross-network feature fusion strategy was designed based on user-information-topic meta-path to enhance node feature representation and generate user fusion feature vectors with semantic consistency. Finally, user roles were identified in an unsupervised manner using the k-means clustering algorithm, with t-distributed stochastic neighbor embedding (t-SNE) employed for visual validation. Experiments on real-world social media public opinion datasets demonstrated that the proposed model effectively integrates multi-source heterogeneous information, enhancing both the accuracy and interpretability of user role identification. Ablation studies further validated the effectiveness of each module. The proposed method not only offers a novel technical approach for public opinion analysis but also provides a scientific basis for implementing differentiated and precise governance strategies through its interpretable feature fusion mechanism.
|
|
Received: 28 July 2025
|
|
|
|
1 崔韦. 法媒: 全球社交媒体用户突破50亿, 脸书用户数量最多[EB/OL]. (2024-02-02) [2025-07-17]. https://3w.huanqiu.com/a/de583b/4GPsKbknf7Y.
2 张树森, 梁循, 齐金山. 社会网络角色识别方法综述[J]. 计算机学报, 2017, 40(3): 649-673.
3 Forestier M, Stavrianou A, Velcin J, et al. Roles in social networks: methodologies and research issues[J]. Web Intelligence and Agent Systems, 2012, 10(1): 117-133.
4 王熹徽, 林佳雯, 汪翔. 基于社交媒体用户数据的突发事件舆情网络结构与谣言治理[J]. 系统管理学报, 2025, 34(5): 1342-1354.
5 刘勘, 范琴. 基于链路结构的微博领域专家识别研究[J]. 情报学报, 2016, 35(1): 66-76.
6 谭雪晗, 涂艳, 马哲坤. 基于SNA的事故灾难舆情关键用户识别及治理[J]. 情报学报, 2017, 36(3): 297-306.
7 Maji G, Namtirtha A, Dutta A, et al. Influential spreaders identification in complex networks with improved k-shell hybrid method[J]. Expert Systems with Applications, 2020, 144: 113092.
8 王晰巍, 贾若男, 韦雅楠, 等. 多维度社交网络舆情用户群体聚类分析方法研究[J]. 数据分析与知识发现, 2021, 5(6): 25-35.
9 李纲, 李显鑫, 巴志超, 等. 微信群潜水者角色识别及行为动因分析[J]. 图书情报工作, 2018, 62(16): 61-71.
10 王振林, 王松岩. 米德的“符号互动论”解义[J]. 吉林大学社会科学学报, 2014, 54(5): 116-121, 174-175.
11 张庆熊. 符号互动论的社会理论: 以布鲁默为中心的考察[J]. 社会科学, 2024(4): 13-23.
12 殷杰, 王亚男. 社会科学中复杂系统范式的适用性问题[J]. 中国社会科学, 2016(3): 62-79, 205-206.
13 Reich S, Schneider F M, Heling L. Zero likes-symbolic interactions and need satisfaction online[J]. Computers in Human Behavior, 2018, 80: 97-102.
14 Naeem M, Ozuem W, Ranfagni S, et al. User generated content and brand engagement: exploring the role of electronic semiotics and symbolic interactionism on Instagram[J]. Computers in Human Behavior, 2025, 168: 108642.
15 Chen R R, Davison R M, Ou C X. A symbolic interactionism perspective of using social media for personal and business communication[J]. International Journal of Information Management, 2020, 51: 102022.
16 黄晓京. 符号互动理论——库利、米德、布鲁默[J]. 国外社会科学, 1984(12): 56-59.
17 段松青, 于兴隆, 吴斌, 等. 基于有向拓扑势的用户角色分析方法[J]. 通信学报, 2014, 35(12): 124-135.
18 Nagurney A, Dong J E, Zhang D. A supply chain network equilibrium model[J]. Transportation Research Part E: Logistics and Transportation Review, 2002, 38(5): 281-303.
19 Ma N, Liu Y J. SuperedgeRank algorithm and its application in identifying opinion leader of online public opinion supernetwork[J]. Expert Systems with Applications, 2014, 41(4): 1357-1368.
20 刘贞国, 朱宇, 赵海兴, 等. 基于平移约束的异质超网络表示学习[J]. 中文信息学报, 2022, 36(12): 74-84.
21 Wang G H, Wang Y S, Liu K D, et al. A classification and recognition algorithm of key figures in public opinion integrating multidimensional similarity and k-shell based on supernetwork[J]. Humanities and Social Sciences Communications, 2024, 11(1): Article No.262.
22 陈舒婷, 疏学明, 胡俊, 等. 基于时序超网络模型的突发事件网络舆情热点话题发现与演化[J]. 清华大学学报(自然科学版), 2023, 63(6): 968-979.
23 胡秉德, 王新根, 王新宇, 等. 超图学习综述: 算法分类与应用分析[J]. 软件学报, 2022, 33(2): 498-523.
24 齐金山, 梁循, 李志宇, 等. 大规模复杂信息网络表示学习: 概念、方法与挑战[J]. 计算机学报, 2018, 41(10): 2394-2420.
25 吴越, 王英, 王鑫, 等. 基于超图卷积的异质网络半监督节点分类[J]. 计算机学报, 2021, 44(11): 2248-2260.
26 Liu M Y, Liu J, Dong Y X, et al. Interest-driven community detection on attributed heterogeneous information networks[J]. Information Fusion, 2024, 111: 102525.
27 Sang L, Xu M, Qian S S, et al. Context-dependent propagating-based video recommendation in multimodal heterogeneous information networks[J]. IEEE Transactions on Multimedia, 2021, 23: 2019-2032.
28 Wang H, Ma C, Chen H S, et al. Full reconstruction of simplicial complexes from binary contagion and Ising data[J]. Nature Communications, 2022, 13: Article No.3043.
29 沈旺, 时倩如, 王俊尧, 等. 基于超图的在线社交网络信息传播模型研究[J]. 情报学报, 2023, 42(3): 354-364.
30 田儒雅, 刘怡君, 牛文元. 舆论超网络的领袖引导模型[J]. 中国管理科学, 2014, 22(10): 136-141.
31 Ghiassi M, Skinner J, Zimbra D. Twitter brand sentiment analysis: a hybrid system using n-gram analysis and dynamic artificial neural network[J]. Expert Systems with Applications, 2013, 40(16): 6266-6282.
32 彭丽徽, 李贺, 张艳丰. 基于灰色关联分析的网络舆情意见领袖识别及影响力排序研究——以新浪微博“8·12滨海爆炸事件”为例[J]. 情报理论与实践, 2017, 40(9): 90-94.
33 Poria S, Cambria E, Bajpai R, et al. A review of affective computing: from unimodal analysis to multimodal fusion[J]. Information Fusion, 2017, 37: 98-125.
34 E J W, Zhang Y L, Xia X W, et al. TANGNN: a concise, scalable and effective graph neural networks with Top-m attention mechanism for graph representation learning[J]. Expert Systems with Applications, 2025, 271: 126599.
35 张鑫蕊, 张海涛, 栾宇, 等. 突发事件信息协同超网络的构建方法研究[J]. 情报学报, 2023, 42(9): 1040-1051.
36 Fu C G. Tracking user-role evolution via topic modeling in community question answering[J]. Information Processing & Management, 2019, 56(6): 102075.
37 van der Maaten L, Hinton G. Visualizing data using t-SNE[J]. Journal of Machine Learning Research, 2008, 9: 2579-2605.
38 Allaoui M, Belhaouari S B, Hedjam R, et al. t-SNE-PSO: optimizing t-SNE using particle swarm optimization[J]. Expert Systems with Applications, 2025, 269: 126398.
39 王宁, 郭梓昱, 田淑珂, 等. 基于融合特征t-SNE降维的控制图质量异常模式识别[J]. 系统工程理论与实践, 2024, 44(7): 2381-2393.
40 Freeman L C. A set of measures of centrality based on betweenness[J]. Sociometry, 1977, 40(1): 35-41.
41 Kitsak M, Gallos L K, Havlin S, et al. Identification of influential spreaders in complex networks[J]. Nature Physics, 2010, 6(11): 888-893.
42 Bonacich P F. Factoring and weighting approaches to status scores and clique identification[J]. The Journal of Mathematical Sociology, 1972, 2(1): 113-120.
43 杨瑞仙, 于政杰, 钟茜, 等. 融合多用户属性的网络知识社区核心用户识别研究: 基于情感加权的LeaderRank算法[J]. 情报学报, 2024, 43(6): 685-696.
44 Nie Y P, Jia Y, Li S D, et al. Identifying users across social networks based on dynamic core interests[J]. Neurocomputing, 2016, 210: 107-115. |
|
|
|
