数据与计算发展前沿 ›› 2021, Vol. 3 ›› Issue (4): 126-139.

doi: 10.11871/jfdc.issn.2096-742X.2021.04.011

• 技术与应用 • 上一篇    下一篇

基于综合影响力和情感特征的意见领袖发现方法

王嘉麒1,2(),杜义华1,*(),赵以霞1()   

  1. 1.中国科学院计算机网络信息中心,北京 100190
    2.中国科学院大学,北京 100049
  • 收稿日期:2021-02-22 出版日期:2021-08-20 发布日期:2021-08-30
  • 通讯作者: 杜义华
  • 作者简介:李浩,中国科学院计算机网络信息中心,硕士研究生,研究方向为大型信息系统开发技术。
    本文承担的工作为区块链电子发票应用平台的技术调研及系统方案设计与实现。
    LI Hao is a master student at Computer Network Information Center, Chinese Academy of Sciences. His main research inter-est is large-scale information system development technology.
    In this paper, he is mainly responsible for literature survey, platform overview design and realization.
    E-mail: lihao@cnic.cn|李新,中国科学院计算机网络信息中心,博士后,副研究员,研究方向为大型信息系统开发技术、软件项目管理等。
    本文承担的工作为基于区块链的电子发票应用平台整体架构设计。
    LI Xin, postdoctoral, is an associate research fellow at Comp-uter Network Information Center, Chinese Academy of Sciences. His main research interests include large-scale information system development technology, software project management and other related technologies.
    In this paper, he is mainly responsible for the overall frame-work design.
    E-mail: lixin@cnic.cn|陈远平,中国科学院计算机网络信息中心,硕士,高级工程师,研究方向为数据分析、决策分析模型研究、数据挖掘应用。
    本文承担的工作为基于区块链的电子发票应用平台接口设计。
    CHEN Yuanping, master degree, is an associate research fellow at Computer Network Information Center, Chinese Academy of Sciences. His main research interests include data analysis, decision analysis model research and data mining application.
    In this paper, he is mainly responsible for the overall API des-ign of Blockchain Platform.
    E-mail: ypchen@cnic.cn|王嘉麒,中国科学院计算机网络信息中心,中国科学院大学,硕士研究生,主要研究方向为传播分析与引导、中文情感分析。
    本文中负责数据采集,实验设计和实现。
    WANG Jiaqi is a master student at Computer Network Infor-mation Center of the Chinese Academy of Sciences and Univ-ersity of the Chinese Academy of Sciences. His main research directions are public opinion communication analysis and gui-dance, and Chinese sentiment analysis.
    In this paper, he is responsible for dataset construction, experi-mental design and implementation.
    E-mail: wangjiaqi@cnic.cn|杜义华,中国科学院计算机网络信息中心,高级工程师,部门副主任,硕士生导师,主要研究方向为传播分析与引导、软件设计开发。
    本文中负责结论展望。
    DU Yihua, Master Supervisor, is a senior engineer and deputy department director at Computer Network Information Center of the Chinese Acad-emy of Sciences. His research directions are public opinion communication analysis and guidance, and software design and development.
    In this paper, he is responsible for the conclusion outlook.
    E-mail: yhdu@cashq.ac.cn|赵以霞,中国科学院计算机网络信息中心,高级工程师,主要研究方向为在线学习技术。
    本文中负责研究现状介绍。
    ZHAO Yixia is a senior engineer at Com-puter Network Information Center of the Chinese Academy of Sciences. Her research direction is online learning technology.
    In this paper, she is responsible for the current studying status introduction.
    E-mail: zyx@cnic.cn
  • 基金资助:
    中国科学院战略性先导科技专项(C类)(XDC02060100)

A Method of Opinion Leader Discovery Based on Comprehensive Influence and Sentiment Characteristics

WANG Jiaqi1,2(),DU Yihua1,*(),ZHAO Yixia1()   

  1. 1. Computer Network Information Center, Chinese Academy of Sciences, Beijing 100190, China
    2. University of Chinese Academy of Sciences, Beijing 100049, China
  • Received:2021-02-22 Online:2021-08-20 Published:2021-08-30
  • Contact: DU Yihua

摘要:

【目的】针对传统意见领袖发现方法局限于部分数据特征导致忽略部分意见领袖的现象,提出一种基于综合影响力和情感特征的发现方法CI-SC,可筛查出部分被传统方法忽略的意见领袖。【方法】综合考虑用户在个人属性和互动行为两方面的特征作为综合影响力,同时引入情感特征,通过聚类分析发现意见领袖,并根据身份信息和社交关系评价结果。【结果】本方法能有效地发现意见领袖,结果具有统计学显著性。本方法与传统方法的发现结果重合率较低,证明可以有效发现部分被传统方法忽略的意见领袖。【局限】目前只在有限规模数据集中进行了实验,其有效性需在更大规模数据集中进一步验证。【结论】提出了基于综合影响力和情感特征的意见领袖发现方法,实验证明此方法能有效发现被传统方法忽略的部分意见领袖,可作为传统方法的补充,在舆情分析与引导中具有一定实用价值。

关键词: 电子发票, 区块链, 重复报销, 信息不可篡改, CI-SC, 影响力, 情感极性, 意见领袖发现

Abstract:

[Objective] In response to the phenomenon that traditional opinion leader discovery methods are limited to partial data features and lead to ignoring of some opinion leaders, this paper proposes a new opinion leader discovery method called CI-SC to achieve the purpose of discovering the ignored opinion leaders. [Methods] CI-SC integrates the influence characteristics of users in both profile attributes and post interaction behaviors to build a comprehensive influence evaluation index. By introducing users' sentiment characteristics, CI-SC achieves the discovery of opinion leaders through cluster analysis based on the above characteristics. The results are evaluated by analyzing identity information and social connections. [Results] According to the experimental results, the opinion leaders found by our method have higher statistical significance and lower overlap ratio compared with those found by traditional methods, which means that by considering more aspects of information, our method can effectively identify opinion leaders with greater influence and obvious sentiment characteristics that are ignored by traditional methods. [Limitations] The proposed method has only been tested on a small dataset so far. Thus, more experiments on larger datasets are needed to further validate its effectiveness. [Conclusions] This paper proposed a new opinion leader discovery method called CI-SC, which is based on comprehensive influence and sentiment characteristics. Experimental results prove that by taking into account the influence of a user in different aspects and further combining the influence with the sentiment characteristics, CI-SC improves the traditional opinion leader discovery methods in discovering opinion leaders without neglecting some information. Therefore, our method can be an effective supplement to traditional methods and has practical value in opinion analysis and guidance.

Key words: electronic invoice, block chain, duplicate reimbursement, information immutability, CI-SC, influence, sentiment polarity, opinion leader discovery