Virtual Identity Identification Based on Semantic for Network Trading Platform

doi:10.3969/j.issn.1671-1122.2020.12.007

Abstract

Abstract:

In recent years, the development of IT technology has given rise to the prosperity of online trading platforms, which are deeply integrated into people's production and life. The diversification and differentiation of online transactions also encourage both parties to register accounts on different platforms and use multiple virtual identities to buy and sell commodities. Due to the non-sharing of information between different platforms and the lack of effective association between virtual identities, data cannot be aggregated and it is difficult to identify users through the traditional data association comparison method. Therefore, new technical methods are urgently needed to effectively identify the virtual identities of participants of network trading platforms and form accurate identity mapping. Training data using multiple network trading platform, this paper generated virtual identity based on Doc2Vec semantic similarity analysis identity recognition unsupervised model, description of goods on sale text similarity calculation, dig the hidden sellers in the same virtual identity, and picture for the user, recommend, risk control and other technical application support.

Key words: Doc2Vec, virtual identity profiling, semantic similarity

CLC Number:

TP309

ZHANG Xuan, YUAN Deyu, JIN Bo. Virtual Identity Identification Based on Semantic for Network Trading Platform[J]. Netinfo Security, 2020, 20(12): 47-53.

Figures/Tables 8

References 21

[1]	GUAN Haotian. Research on Virtual Identity Mapping Algorithm for Network Sapce Entity[D]. Harbin: Harbin Institute of Technology, 2019.
	关皓天. 网络空间主体虚拟身份映射算法研究[D]. 哈尔滨:哈尔滨工业大学, 2019.
[2]	ZHANG Yiming, XIONG Qi, FAN Yujie, et al. Your Style Your Identity: Leveraging Writing and Photography Styles for Drug Trafficker Identification in Darknet Markets over Attributed Heterogeneous Information Network[C]// WWW. 19th The World Wide Web Conference, May 2019, New York, NY, USA. San Francisco: Association for Computing Machinery, 2019: 3448-3454.
[3]	LI Cong. Research on Virtual Identity Tracing and Forensics[D]. Chongqing: Chongqing University of Posts and Telecommunications, 2018.
	李葱. 虚拟身份追踪与取证研究[D]. 重庆:重庆邮电大学, 2018.
[4]	DING Xiang. Research and Implementation of Tor Darknet Content Discovery and Analysis Technology[D]. Nanjing: Southeast University of China, 2019.
	丁翔. Tor暗网内容发现与分析技术的研究和实现[D]. 南京:东南大学, 2019.
[5]	YANG Yi. Darknet Resource Exploring Technology Research Based on Tor[D]. Shanghai: Shanghai Jiao Tong University, 2018.
	杨溢. 基于Tor的暗网空间资源探测技术研究[D]. 上海:上海交通大学, 2018.
[6]	KADOGUCHI M, HAYASHI S, HANSHIMOTO, et al. Exploring the Dark Web for Cyber Threat Intelligence Using Machine Leaning[C]// IEEE. 2019 IEEE International Conference on Intelligence and Security Informatics (ISI). Shenzhen, China, IEEE, 2019: 200-202.
[7]	ZHANG Shusen, LIANG Xun, MI Baotong, et al. Content-Based Social Network User Identification Methods[J]. Chinese Journal of Computers, 2019,42(8):1739-1754.
	张树森, 梁循, 弭宝瞳, 等. 基于内容的社交网络用户身份识别方法[J]. 计算机学报, 2019,42(8):1739-1754.
[8]	XU Qian, CHEN Hongchang, WU Zheng, et al. User Identification Method Across Social Networks Based on Weighted Hypergraph[J]. Journal of Computer Applications, 2017, 37(12): 3435-3441+3471.
	徐乾, 陈鸿昶, 吴铮, 等. 基于带权超图的跨网络用户身份识别方法[J]. 计算机应用, 2017, 37(12): 3435-3441+3471.
[9]	SITIKHU P, PAHI K, THPAPA P, et al. A Comparison of Semantic Similarity Methods for Maximum Human Interpretability[C]// IEEE. Artificial Intelligence for Transforming Business and Society (AITB). November 2019, Kathmandu, Nepal. New York: IEEE, 2019: 5-5
[10]	LIN Dekang. An Information-theoretic Definition of Similarity[C]// ICML. The 15th International Conference on Machine Learning. July 1998, San Francisco, CA, USA. Morgan Kaufmann Publishers Inc., 1998: 296-304.
[11]	CHEN Erjing, JIANG Enbo. Review of Studies on Text Similarity Measures[J]. Data Analysis and Knowledge Discovery, 2017,1(6):1-11.
	陈二静, 姜恩波. 文本相似度计算方法研究综述[J]. 数据分析与知识发现, 2017,1(6):1-11.
[12]	WANG Chunliu, YANG Yonghui, DENG Fei, et al. A Review of Text Similarity Approaches[J]. Information Science, 2019,37(3):158-168.
	王春柳, 杨永辉, 邓霏, 等. 文本相似度计算方法研究综述[J]. 情报科学, 2019,37(3):158-168.
[13]	ZHANG Shuang, ZHENG Xuefeng, HU Chuangjun. Survey of Semantic Similarity and its Application to Social Network Analysis[C]// IEEE. 2015 IEEE International Conference on Big Data (Big Data), January 2020, Santa Clara, CA, USA. New York: IEEE, 2015: 2362-2367
[14]	HAN Chengcheng, LI Lei, LIU Tingting, et al. Approaches for Semantic Textual Similarity[J]. Journal of East China Normal University(Natural Science), 2020(5):95-112.
	韩程程, 李磊, 刘婷婷, 等. 语义文本相似度计算方法[J]. 华东师范大学学报(自然科学版), 2020(5):95-112.
[15]	YANG Cheng. Research on Semantic Similarity Calculation of Short Text Based on Neural Network[D]. Chengdu: University of Electronic Science and Technology of China, 2020.
	杨晨. 基于神经网络的短文本语义相似度计算方法研究[D]. 成都:电子科技大学, 2020.
[16]	QUOC L, TOMAS M. Distributed Representations of Sentences and Documents[C]// ACM. In Proceedings of the 31st International Conference on International Conference on Machine Learning, June 2014, Beijing, China. New York: JMLR. org, 2014: 1188-1196.
[17]	YVES P. Comparing Sentence Similarity Methods[EB/OL]. http://nlp.town/blog/sentence-similarity/, 2018-05-02.
[18]	WANG Xiangwen, PENG Peng, WANG Chun, et al. You are Your Photographs: Detecting Multiple Identities of Vendors in the Darknet Marketplaces[C]// ACM. ASIA CCS '18: ACM Asia Conference on Computer and Communications Security, June 2018, Incheon Republic of Korea. New York: Association for Computing Machinery, 2018: 431-442.
[19]	SUN Junyi, WANG Dingyuan, XIANG Chao, et al. "Jieba"Chinese Word Segmentation[EB/OL]. https://github.com/fxsjy/jieba, 2020-10-20.
[20]	LUO Ruixuan, XU Jingjing, REN Xuancheng. Pkuseg[EB/OL]. https://github.com/lancopku/pkuseg-python, 2020-06-21.
[21]	RADIM R, PETR S. Genism[EB/OL]. https://radimrehurek.com/gensim/index.html 2019-11-01.

站点名称	交易发帖量/条
交易论坛1	22138
交易论坛2	2297
交易论坛3	263

算法	Top-1 Accurracy
算法	cs	scs
TF-IDF	0.741035857	0.760956175
Word2Vec	0.844621514	0.87250996
Doc2Vec	0.900318725	0.922191235