电子学报 ›› 2016, Vol. 44 ›› Issue (7): 1714-1720.DOI: 10.3969/j.issn.0372-2112.2016.07.028

• 学术论文 • 上一篇    下一篇

一种在线社交网络的自适应观点引导模型及实现

许文文1, 时鹏2, 于留宝3, 胡长军1   

  1. 1. 北京科技大学计算机与通信工程学院, 北京 100083;
    2. 北京科技大学国家材料服役安全科学中心, 北京 100083;
    3. 微梦创科网络科技(中国)有限公司, 北京 100080
  • 收稿日期:2015-02-04 修回日期:2015-05-07 出版日期:2016-07-25 发布日期:2016-07-25
  • 通讯作者: 时鹏
  • 作者简介:许文文 女,1989年5月出生于山西临汾.北京科技大学博士研究生,研究方向为社交网络中信息传播分析.E-mail:xuwenwenustb@163.com
  • 基金资助:

    国家973重点基础研究发展计划(No.2013CB329605)

An Adaptive Opinion Guiding Model for Online Social Networks

XU Wen-wen1, SHI Peng2, YU Liu-bao3, HU Chang-jun1   

  1. 1. School of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing 100083, China;
    2. National Center for Materials Service Safety, University of Science and Technology Beijing, Beijing 100083, China;
    3. The Micro Dreaming of Beijing Network Technology Company Limited, Beijing 100080, China
  • Received:2015-02-04 Revised:2015-05-07 Online:2016-07-25 Published:2016-07-25

摘要:

在线社交网络已成为信息传播的重要途径,给人们获取信息带来便利的同时,也为不良信息的扩散提供了温床.目前主流的在线社交网络都采用关键字匹配的方式屏蔽不良信息的发布,在阻止信息本身的同时,也屏蔽了与其相关的积极观点的传播.本文提出一种自适应的观点引导模型,实现对在线社交网络用户的观点引导.该模型首先分析网络用户对事件/事物的观点和情感倾向,确定其中观点消极的用户作为引导对象,然后向其推送与之关注点相近且情感相对积极的信息或用户,进行观点引导,同时引入反馈机制,根据引导对象的观点变化动态调整推送内容,以实现长期精确引导.基于该模型设计并实现了观点引导系统,包括引导信息模块、观点标注模块、推荐模块和反馈模块,实现了自动选择群体、自动识别群体情感倾向、自动选择和调整推送内容等功能.实验结果表明,该模型能够实现对在线社交网络用户的观点引导.

关键词: 在线社交网络, 观点引导, 情感分析, 内容推荐

Abstract:

Online social networks are now recognized as an important platform for the spread of information. While providing convenient exchange for users,it also makes OSNs fertile grounds for the wide spread of misinformation which can lead to undesirable consequences.Most mainstream media outlets use keyword matching as a search method to find misinformation and forbid the presentation in context.However,this method also blocks positive messages related to misinformation.In this paper,we propose an adaptive opinion guiding model to limit the spread of misinformation.Based on user's opinion and sentiment,the model recommends messages or other users that have relative positive feeling to current user.It also introduces the feedback mechanism to achieve a long-term and accurate guiding by adjusting the pushing content dynamically.We also design and finish the guiding system.Experiments show that the model can guide the opinion of the network group effectively.

Key words: online social networks, opinion guiding, sentiment analysis, content-based recommendation

中图分类号: