首页 | 本学科首页   官方微博 | 高级检索  
     检索      

基于动态演化的讨论帖流行度预测
引用本文:孔庆超,毛文吉.基于动态演化的讨论帖流行度预测[J].软件学报,2014,25(12):2767-2776.
作者姓名:孔庆超  毛文吉
作者单位:中国科学院自动化研究所复杂系统管理与控制国家重点实验室,北京,100190
基金项目:国家自然科学基金(61175040,71025001)
摘    要:互联网用户间的交互行为,使得某些用户生成的内容(如讨论帖、微博话题)变得流行。对所关注内容的流行度进行建模和预测,在多个领域中具有十分重要的研究和应用价值。针对论坛讨论帖的流行度预测问题,基于早期的发展演化信息,探讨了影响讨论帖流行度的相关动态因素,并提出一种结合局部特性、融合多个动态因素的讨论帖流行度预测算法。以豆瓣小组的数据为例,对所提出的算法进行实验。实验结果表明,所提出的融合多种动态因素的方法与基准方法相比,能够较好地预测讨论帖的流行度。

关 键 词:用户生成的内容  内容流行度  流行度预测  社会媒体分析  动态演化建模与预测
收稿时间:5/6/2014 12:00:00 AM
修稿时间:2014/8/21 0:00:00

Predicting Popularity of Forum Threads Based on Dynamic Evolution
KONG Qing-Chao and MAO Wen-Ji.Predicting Popularity of Forum Threads Based on Dynamic Evolution[J].Journal of Software,2014,25(12):2767-2776.
Authors:KONG Qing-Chao and MAO Wen-Ji
Institution:State Key Laboratory of Management and Control for Complex Systems (Institute of Automation, The Chinese Academy of Sciences), Beijing 100190, China;State Key Laboratory of Management and Control for Complex Systems (Institute of Automation, The Chinese Academy of Sciences), Beijing 100190, China
Abstract:Web user's online interacting behavior with others usually makes some user generated content (e.g. forum threads and Weibo topics) popular. The modeling and prediction of the popularity of online content are of great research importance and practical value in many different domains. To predict the popularity of forum threads, this paper discusses several dynamic factors that might affect the popularity of online content based on the information of dynamic evolution at the early stage, and proposes a popularity prediction algorithm which makes use of the locality property and combines multiple dynamic factors. The proposed algorithm is further evaluated with the Douban group dataset. The experimental results show that, compared with the baseline methods, our method achieves relatively better performance in predicting the popularity of forum threads.
Keywords:user generated content  popularity of online content  popularity prediction  social media analytics  modeling and prediction of dynamic evolution
本文献已被 CNKI 万方数据 等数据库收录!
点击此处可从《软件学报》浏览原始摘要信息
点击此处可从《软件学报》下载免费的PDF全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号