Reputation Evaluation Model in Social Network Based on Information Behavior

doi:10.3969/j.issn.1671-1122.2021.12.008

Abstract

Abstract:

In order to promote self-discipline and autonomy of social network users and improve the credibility of social network, a dynamic reputation evaluation method based on user information behavior supervision and feedback is studied. The comprehensive reputation contains identity and behavior reputation, set evaluation period for a new node and update mechanism in different stage. Identity reputation is calculated by information disclosure and network characteristics; behavior reputation is calculated by information release and forwarding, and rewards or punishments will be given to self correction of information behavior or blocking of bad information. The simulation results show that compared with the traditional trust evaluation mechanism, setting rewards and punishments guidance can improve the accuracy of reputation evaluation. Reputation incentive can also inhibit the interaction of bad information.

Key words: social network, reputation, information behavior, reputation rewards and punishments, network governance

CLC Number:

TP309

XIONG Jianying. Reputation Evaluation Model in Social Network Based on Information Behavior[J]. Netinfo Security, 2021, 21(12): 51-59.

Figures/Tables 8

References 16

[1]	WEI Lulu. The Regulation Responsibility of Social Media Platforms over Its Content from the Perspective of Internet Innovation[J]. Oriental Law, 2020, 13(1):27-33.
	魏露露. 互联网创新视角下社交平台内容规制责任[J]. 东方法学, 2020, 13(1):27-33.
[2]	JAZAIERI H, LOGLI ALLISON M, CAMPOS B, et al. Content, Structure, and Dynamics of Personal Reputation: The Role of Trust and Status Potential within Social Networks[J]. Group Processes & Intergroup Relations, 2019, 22(7):964-983
[3]	WANG Gang. Literature Review on Network Information Behavior of Domestic Based on Virtual Community[J]. Library, 2017, 45(5):47-53.
	王刚. 基于虚拟社区的国内网络信息行为研究综述[J]. 图书馆, 2017, 45(5):47-53.
[4]	NIE Yonghao, LUO Jingyue. Perceived Usefulness, Trust and Personal Information Disclosure Intention of Social Networking Site Users[J]. Documentation, Information & Knowledge, 2013, 31(5):89-97.
	聂勇浩, 罗景月. 感知有用性、信任与社交网站用户的个人信息披露意愿[J]. 图书情报知识, 2013, 31(5):89-97.
[5]	ZHANG Changliang, WANG Xiwei, WANG Yameng, et al. Research on the Development Trend of User Information Behavior in Virtual Community[J]. Information Science, 2018, 36(3):157-163. doi: 10.1016/0020-0255(85)90029-5 URL
	张长亮, 王晰巍, 王雅梦, 等. 网络社群用户信息行为发展动态及趋势研究[J]. 情报科学, 2018, 36(3):157-163.
[6]	LIU Yahui, JIN Xiaolong, SHEN Huawei, et al. A Survey on Rumor Identification over Social Media[J]. Chinese Journal of Computers, 2018, 41(7):108-130.
	刘雅辉, 靳小龙, 沈华伟, 等. 社交媒体中的谣言识别研究综述[J]. 计算机学报, 2018, 41(7):108-130.
[7]	ZHANG Dayong, SUN Xiaochen. Identifying the Influencing Factors of Users Information Contribution Behavior on Social Network Sites[J]. Information Science, 2018, 36(2):95-100.
	张大勇, 孙晓晨. 社交网络用户信息贡献行为影响因素分析[J]. 情报科学, 2018, 36(2):95-100.
[8]	ZHANG Huiping, GUO Xinhao, TANG Zhiwei. Impact of Sanction Mechanism on Behavioral Intention to Identify Internet Rumor[J]. Journal of Intelligence, 2016, 35(12):47-51.
	张会平, 郭昕昊, 汤志伟. 惩罚机制对网络谣言识别行为的影响研究[J]. 情报杂志, 2016, 35(12):47-51.
[9]	URENA R, CHICLANA F, CARRASCO R A, et al. Leveraging Users’ Trust and Reputation in Social Networks[J]. Procedia Computer Science, 2019, 162(12):955-962. doi: 10.1016/j.procs.2019.12.073 URL
[10]	YU Zhen, ZHU Jie, SHEN Guicheng. Trust Model and Simulation of E-commerce Based on Social Networks[J]. Journal of System Simulation, 2018, 30(8):304-312.
	于真, 朱杰, 申贵成. 一种基于社交网络的电子商务信任模型与仿真[J]. 系统仿真学报, 2018, 30(8):304-312.
[11]	ZHAO Lihua, YANG Yong, WEN Xi, et al. Research on the Evaluation of Micro-blog Users’ Credibility Based on Public Data[J]. Journal of Tianjin University(Social Sciences), 2018, 20(3):29-35.
	赵丽华, 杨勇, 闻西, 等. 基于公开信息的微博用户可信性评价研究[J]. 天津大学学报(社会科学版), 2018, 20(3):29-35.
[12]	ZHANG Jidong, LI Pengcheng. Research on Constructing Quantitative Model of User Trust in Mobile Social Network[J]. Information Studies: Theory & Application, 2017, 40(5):56-60.
	张继东, 李鹏程. 移动社交网络用户信任度量化模型构建研究[J]. 情报理论与实践, 2017, 40(5):56-60.
[13]	ZHANG Ning, SU Hua, SUN Xuemei, et al. Crowd Sensing Network User Participation Incentive Mechanism Based on Credibility Model[J]. Computer Applications and Software, 2017, 34(5):119-122.
	张宁, 苏华, 孙学梅, 等. 基于信誉模型的群智感知网络用户参与激励机制[J]. 计算机应用与软件, 2017, 34(5):119-122.
[14]	TENG Jie, XIA Zhijie, LUO Mengying, et al. Research on Trust Recognition of Information Subject in Network Rumor Propagation Event Based on Multi-Agent[J]. Journal of Intelligence, 2020, 39(3):105-114.
	滕婕, 夏志杰, 罗梦莹, 等. 基于Multi-Agent的网络谣言传播事件中信息主体信任识别研究[J]. 情报杂志, 2020, 39(3):105-114.
[15]	DAI Bao, LIU Yezheng. Review on the Influence Factors of SNS Users' Information Behavior[J]. Information Science, 2016, 34(6):170-176.
	代宝, 刘业政. SNS用户信息行为的影响因素研究综述[J]. 情报科学, 2016, 34(6):170-176.
[16]	GIANLUCA, GIUSEPPE M L S. CellTrust: a Reputation Model for C2C Commerce[J]. Electron Commerce Research, 2008, 8(4):193-216. doi: 10.1007/s10660-008-9019-8 URL

属性	不合理评判规则
姓名	国籍为中国时,含非中文字符：0 国籍为中国时,长度小于2：0 汉族条件下,长度大于4：0.5 汉族条件下,第一个字符不能匹配姓氏库样本：0.5
年龄	年龄小于6或年龄大于120：0 在职状态：年龄低于18或高于80：0 学生状态：年龄低于6或高于45：0.5
毕业学校	校名库中无学校信息：0.5
所属组织	组织库中无组织信息：0.5

属性	属性内涵	离散规则
行业	从业类型	专业性职业 1,学生 0.5,非专业性职业0
组织	组织规模	高规模1,中小规模 0.5,无组织0
学历	知识水平	研究生以上 1,大中专0.5,高中及以下 0
职称	从业资历	高级1,中级 0.5,初级0

维度	信息行为	解释	奖惩规则	系数r
内容核查	原创加精	对所发布原创内容,根据其点击量、转发量等设置为精华贴	每增加1条精华帖	+0.01
	发布不良信息	发布不良信息,受到平台对其核查	每核实发布1条	-0.03
	转发不良信息	转发不良信息,受到平台对其核查	每核实发布1条	-0.02
自我纠偏	删除不良信息	在未被平台核实之前删除,澄清	每核实曾发布1条	-0.01
传播阻断	有效举报	自觉核查信息,在平台对不良信息进行举报,	每核实有效1条	+0.02
传播阻断	无效举报	未核查信息,无有效证据,违规举报	每核实无效1条	-0.01