基于异质图注意力网络与多特征融合的跨社交媒体用户识别研究

doi:10.3772/j.issn.1000-0135.2024.10.007

情报学报

2024, Vol. 43

Issue (10): 1213-1226 DOI: 10.3772/j.issn.1000-0135.2024.10.007

情报技术与应用

本期目录 | 过刊浏览 | 高级检索

基于异质图注意力网络与多特征融合的跨社交媒体用户识别研究

毕达天, 张雪, 孔婧媛, 陈功坤

吉林大学商学与管理学院，长春 130012

User Identification Across Social Media Based on Heterogeneous Graph Attention Network and Multi-Feature Fusion

Bi Datian, Zhang Xue, Kong Jingyuan, Chen Gongkun

School of Business and Management, Jilin University, Changchun130012

摘要
图/表
参考文献
相关文章 (15)

全文: PDF (2919 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要跨社交媒体用户识别对于网络舆情的协同治理以及用户偏好的全方位识别与预测具有重要的指导意义。针对现有方法存在数据表达能力弱、忽略用户信息的动态性和关联性的问题，本文提出一种融合异质特征嵌入与实体动态关联的跨社交媒体用户识别模型。首先，整合用户的基本属性、生成内容和社交结构信息，构建各个社交媒体的异质信息网络；其次，通过设计新的元路径识别策略构造邻接矩阵，使用异质图注意力网络模型汇聚用户节点信息，增强节点特征的表示能力；再其次，引入了3种连续时间衰减函数，对跨社交媒体的实体相似矩阵进行加权，增强实体之间的动态关联；最后，融合单社交网络和跨社交网络中的以上特征，利用多层感知机实现跨社交媒体用户的识别和预测。在微博-知乎真实数据集中的研究结果显示，本文模型的整体性能优于其他基准模型，特别是线性衰减函数，其展现了最佳效果，且本文提出的元路径识别策略对提升用户识别效果具有重要作用。

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	毕达天
	张雪
	孔婧媛
	陈功坤

关键词 ：跨社交媒体, 用户识别, 异质网络, 注意力机制, 命名实体

收稿日期: 2023-10-16

基金资助:国家社会科学基金项目“基于用户跨社交媒体的信息行为偏好特征挖掘与推荐研究”（21BTQ059）。

作者简介: 毕达天，男，1983年生，博士，教授，博士生导师，主要研究领域为社交媒体与用户信息行为，E-mail：bdt@jlu.edu.cn；张雪，女，2000年生，博士研究生，主要研究领域为大数据挖掘与深度学习；孔婧媛，女，1997年生，博士研究生，主要研究领域为社交媒体与自然语言处理；陈功坤，男，2002年生，博士研究生，主要研究领域为信息管理与信息系统；

引用本文:

毕达天, 张雪, 孔婧媛, 陈功坤. 基于异质图注意力网络与多特征融合的跨社交媒体用户识别研究[J]. 情报学报, 2024, 43(10): 1213-1226.
Bi Datian, Zhang Xue, Kong Jingyuan, Chen Gongkun. User Identification Across Social Media Based on Heterogeneous Graph Attention Network and Multi-Feature Fusion. 情报学报, 2024, 43(10): 1213-1226.

链接本文:

https://qbxb.istic.ac.cn/CN/10.3772/j.issn.1000-0135.2024.10.007 或 https://qbxb.istic.ac.cn/CN/Y2024/V43/I10/1213

1 Backlinko Team. Social media usage & growth statistics[EB/OL]. (2024-09-06). https://backlinko.com/social-media-users.
2 Gao H, Wang Y Q, Shao J L, et al. User identity linkage across social networks with the enhancement of knowledge graph and time decay function[J]. Entropy, 2022, 24(11): 1603.
3 张彬, 徐建民, 吴姣. 跨域推荐中的知识融合研究进展[J]. 现代情报, 2023, 43(3): 157-166.
4 刘忠宝, 赵文娟. 融合语义特征和分布特征的跨媒体关联分析方法研究[J]. 情报学报, 2021, 40(5): 471-478.
5 易明, 刘明, 冯翠翠. 融合异质信息网络表示学习的跨领域推荐研究[J]. 情报学报, 2022, 41(4): 337-349.
6 Yang Z G, Lin Z H, Guo L N, et al. MMED: a multi-domain and multi-modality event dataset[J]. Information Processing & Management, 2020, 57(6): 102315.
7 Wang Y Q, Feng C Y, Chen L, et al. User identity linkage across social networks via linked heterogeneous network embedding[J]. World Wide Web, 2019, 22(6): 2611-2632.
8 Diaz J, Poblete B, Bravo-Marquez F. An integrated model for textual social media data with spatio-temporal dimensions[J]. Information Processing & Management, 2020, 57(5): 102219.
9 余艳, 张文, 熊飞宇, 等. 融合知识图谱与神经网络赋能数智化管理决策[J]. 管理科学学报, 2023, 26(5): 231-247.
10 Chung W, Lai V S. A temporal graph framework for intelligence extraction in social media networks[J]. Information & Management, 2023, 60(4): 103773.
11 邢玲, 邓凯凯, 吴红海, 等. 复杂网络视角下跨社交网络用户身份识别研究综述[J]. 电子科技大学学报, 2020, 49(6): 905-917.
12 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.
13 Zafarani R, Liu H. Connecting corresponding identities across communities[J]. Proceedings of the International AAAI Conference on Web and Social Media, 2009, 3(1): 354-357.
14 Li Y J, Peng Y, Zhang Z, et al. A deep dive into user display names across social networks[J]. Information Sciences, 2018, 447: 186-204.
15 Mu X, Zhu F D, Lim E P, et al. User identity linkage by latent user space modelling[C]// Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York: ACM Press, 2016: 1775-1784.
16 齐林峰. 利用实体解析的跨社交媒体同一用户识别[J]. 图书情报工作, 2017, 61(6): 107-114.
17 Li Y J, Ji W L, Gao X, et al. Matching user accounts with spatio-temporal awareness across social networks[J]. Information Sciences, 2021, 570: 1-15.
18 Chen B Y, Chen X L. MAUIL: multilevel attribute embedding for semisupervised user identity linkage[J]. Information Sciences, 2022, 593: 527-545.
19 Li Y J, Zhang Z, Peng Y, et al. Matching user accounts based on user generated content across social networks[J]. Future Generation Computer Systems, 2018, 83: 104-115.
20 Gao M C, Wang R H, Wang L, et al. Cross-domain entity identity association analysis and prediction based on representation learning[J]. International Journal of Distributed Sensor Networks, 2022, 18(11): 15501329221135060.
21 Liu L, Li X, Cheung W K, et al. Structural representation learning for user alignment across social networks[J]. IEEE Transactions on Knowledge and Data Engineering, 2020, 32(9): 1824-1837.
22 Ding X, Zhang H F, Ma C, et al. User identification across multiple social networks based on naive Bayes model[J]. IEEE Transactions on Neural Networks and Learning Systems, 2024, 35(3): 4274-4285.
23 Sergey B, Anton K, Seungtaek P, et al. Joint link-attribute user identity resolution in online social networks[C]// Proceedings of the 6th International Conference on Knowledge Discovery and Data Mining, Workshop on Social Network Mining and Analysis. New York: ACM Press, 2012: 12-16.
24 Qu Y T, Ma H H, Wu H H, et al. A multiple salient features-based user identification across social media[J]. Entropy, 2022, 24(4): 495.
25 Chen D L, Su W, Wu P, et al. Joint multimodal sentiment analysis based on information relevance[J]. Information Processing & Management, 2023, 60(2): 103193.
26 何喜军, 吴爽爽, 武玉英, 等. 基于属性异构网络表示学习的专利交易推荐[J]. 情报学报, 2022, 41(11): 1214-1228.
27 Lin M, Wang T, Zhu Y F, et al. A heterogeneous directed graph attention network for inductive text classification using multilevel semantic embeddings[J]. Knowledge-Based Systems, 2024, 295: 111797.
28 Liu J W, Shi C, Yang C, et al. A survey on heterogeneous information network based recommender systems: concepts, methods, applications and resources[J]. AI Open, 2022, 3: 40-57.
29 Hu D, Feng D, Xie Y L. EGC: a novel event-oriented graph clustering framework for social media text[J]. Information Processing & Management, 2022, 59(6): 103059.
30 Wang X, Ji H Y, Shi C, et al. Heterogeneous graph attention network[C]// Proceedings of the World Wide Web Conference. New York: ACM Press, 2019: 2022-2032.
31 Bing R, Yuan G, Zhu M, et al. Heterogeneous graph neural networks analysis: a survey of techniques, evaluations and applications[J]. Artificial Intelligence Review, 2023, 56(8): 8003-8042.
32 Yang X, Deng C, Liu T L, et al. Heterogeneous graph attention network for unsupervised multiple-target domain adaptation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022, 44(4): 1992-2003.
33 Zhao Y, Wang L L, Wang C, et al. Multi-granularity heterogeneous graph attention networks for extractive document summarization[J]. Neural Networks, 2022, 155: 340-347.
34 Xu Y J, Fang Y, Huang C, et al. HGHAN: hacker group identification based on heterogeneous graph attention network[J]. Information Sciences, 2022, 612: 848-863.
35 Wang R H, Zhu H L, Wang L, et al. User identity linkage across social networks by heterogeneous graph attention network modeling[J]. Applied Sciences, 2020, 10(16): 5478.
36 Qiao S T, Zhou W, Luo F J, et al. Noise-reducing graph neural network with intent-target co-action for session-based recommendation[J]. Information Processing & Management, 2023, 60(6): 103517.
37 陈周国, 丁建伟, 明杨, 等. 基于异质图卷积注意网络的社交媒体账号分类[J]. 计算机系统应用, 2023, 32(7): 269-275.
38 Celik M, Dokuz A S. Discovering socially similar users in social media datasets based on their socially important locations[J]. Information Processing & Management, 2018, 54(6): 1154-1168.
39 叶佳鑫, 熊回香. 基于标签的跨领域资源个性化推荐研究[J]. 数据分析与知识发现, 2019, 3(2): 21-32.
40 卢菁, 王菊钿, 刘丛. 融合多特征的跨社交网络用户在线识别方法研究[J]. 小型微型计算机系统, 2021, 42(11): 2407-2414.
41 吕鲲, 项旻昊, 靖继鹏. 基于LDA2Vec和DTM模型的颠覆性技术主题识别研究——以能源科技领域为例[J]. 图书情报工作, 2023, 67(12): 89-102.
42 Heimann M, Shen H M, Safavi T, et al. REGAL: representation learning-based graph alignment[C]// Proceedings of the 27th ACM International Conference on Information and Knowledge Management. New York: ACM Press, 2018: 117-126.
43 Zhang J, Chen B, Wang X M, et al. MEgo2Vec: embedding matched ego networks for user alignment across social networks[C]// Proceedings of the 27th ACM International Conference on Information and Knowledge Management. New York: ACM Press, 2018: 327-336.
44 陈国青, 张维, 任之光, 等. 面向大数据管理决策研究的全景式PAGE框架[J]. 管理科学学报, 2023, 26(5): 4-22.