基于意见领袖的微博生命周期预测模型研究
|
摘要
为了有效研究社交网络中意见领袖在新浪微博传播所起的作用及微博的生命周期和传播模式,提出了一种OLB微博传播预测模型。通过爬取微博数据进行数据分析,拟合出与影响力有关的四个因素的数学表达式,并通过层次分析法给出权重计算方法;利用计算的影响力以及转发数与相关因素的关系,构建出OLB模型,从而对意见领袖传播作用及微博生命周期进行实验预测分析。仿真结果表明,在微博信息传播中意见领袖影响力与其微博的传播作用成正比例关系,通过误差分析得到四组数据的平均误差值分别为1. 0%、5. 0%、2. 4%及5. 1%,提出的OLB模型对于预测微博传播模式合理、有效。
In order to study the role of opinion leaders in the dissemination of Sina micro-blog and the propagation mode of micro-blog's life cycle in social networks effectively,this paper proposed a propagation prediction OLB model. Firstly,it crawled the micro-blog data,then analyzed the data. Secondly,it fitted a mathematical expression of the four factors related to influence,and gave the weights calculation method through the analytic hierarchy process. Finally,it constructed the OLB model by using the influence of computation and the relationship between forwarding number and related factors. It analyzed the communication role of opinion leaders and micro-blog life cycle through the experiment. The simulation results show that the influence of opinion leaders is positively proportional to the spread of micro-blog in micro-blog information dissemination.The average error of the four sets of data are 1. 0%,5. 0%,2. 4% and 5. 1% respectively by error analysis. The OLB model is reasonable and effective for predicting micro-blog propagation patterns.
In order to study the role of opinion leaders in the dissemination of Sina micro-blog and the propagation mode of micro-blog's life cycle in social networks effectively,this paper proposed a propagation prediction OLB model. Firstly,it crawled the micro-blog data,then analyzed the data. Secondly,it fitted a mathematical expression of the four factors related to influence,and gave the weights calculation method through the analytic hierarchy process. Finally,it constructed the OLB model by using the influence of computation and the relationship between forwarding number and related factors. It analyzed the communication role of opinion leaders and micro-blog life cycle through the experiment. The simulation results show that the influence of opinion leaders is positively proportional to the spread of micro-blog in micro-blog information dissemination.The average error of the four sets of data are 1. 0%,5. 0%,2. 4% and 5. 1% respectively by error analysis. The OLB model is reasonable and effective for predicting micro-blog propagation patterns.
引文
[1]吴渝,马璐璐,林茂,等.基于用户影响力的意见领袖发现算法[J].小型微型计算机系统,2015,36(3):561-565.(Wu Yu,MaLulu,Lin Mao,et al. Discovery algorithm of opinion leaders based onuser influence[J]. Journal of Chinese Computer Systems,2015,36(3):561-565.)
[2]张树森,梁循,齐金山.社会网络角色识别方法综述[J].计算机学报,2017,40(3):649-673.(Zhang Shusen,Liang Xun,Qi Jin-shan. A review on role identification methods in social networks[J].Chinese Journal of Computers,2017,40(3):649-673.)
[3] Li Feng,Du T C. Maximizing micro-blog influence in online promo-tion[J]. Expert Systems with Applications,2017,70(3):52-66.
[4]吴岘辉,张晖,赵旭剑,等.基于用户行为网络的微博意见领袖挖掘算法[J].计算机应用研究,2015,32(9):2678-2683.(WuXianhui,Zhang Hui,Zhao Xujian,et al. Mining algorithm of mi-croblogging opinion leaders based on user-behavior network[J]. Ap-plication Research of Computers,2015,32(9):2678-2683.)
[5] Deng Xiaolong,Li Yuxiao,Lin Shu. Parallel micro blog crawler con-struction for effective opinion leader approximation[J]. AASRI Pro-cedia,2013,5(3):170-176.
[6]李玉贞,胡勇,熊熙,等.微博意见领袖的评估模型[J].信息安全与通信保密,2013(2):79-81.(Li Yuzhen,Hu Yong,Xiong Xi,etal. Evaluation model of micro-blog opinion leader[J]. InformationSecurity and Communications Privacy,2013(2):79-81.)
[7]赵惠东,刘刚,石川,等.基于转发传播过程的微博转发量预测[J].电子学报,2016,44(12):2989-2996.(Zhao Huidong,LiuGang,Shi Chuan,et al. Retweet number prediction based on retweetpropagation process[J]. Acta Electronica Sinica,2016,44(12):2989-2996.)
[8]张仰森,蒋玉茹,陈若愚,等.微博用户关系网络中意见领袖的分析与挖掘[J].北京信息科技大学学报:自然科学版,2015,30(4):7-14.(Zhang Yangsen,Jiang Yuru,Chen Ruoyu,et al. Analy-sis and mining of opinion leaders in microblog user relationship net-work[J]. Journal of Beijing Information Science&TechnologyUniversity:Natural Science Edition,2015,30(4):7-14.)
[9]冯时,景珊,杨卓,等.基于LDA模型的中文微博话题意见领袖挖掘[J].东北大学学报:自然科学版,2013,34(4):490-494.(FengShi,Jing Shan,Yang Zhuo,et al. Detecting topical opinion leadersbased on LDA model in Chinese microblogs[J]. Journal of Nor-th-eastern University:Natural Science,2013,34(4):490-494.)
[10]丁兆云,周斌,贾焰,等.微博中基于多关系网络的话题层次影响力分析[J].计算机研究与发展,2013,50(10):2155-2175.(DingZhaoyun,Zhou Bin,Jia Yan,et al. Topical influence analysis basedon the multi-relational network in microblogs[J]. Journal of Com-puter Research and Development,2013,50(10):2155-2175.)
[11]董雨辰,刘琰,罗军勇,等.基于支持向量机的炒作微博识别方法[J].计算机工程,2015,41(3):7-14.(Dong Yuchen,Liu Yan,LuoJunyong,et al. Hype Microblog recognition method based on supportvector machine[J]. Computer Engineering,2015,41(3):7-14.)
[12]Wei Jiuchang,Bu Bing,Liang Liang. Estimating the diffusion modelsof crisis information in micro blog[J]. Journal of Informetrics,2012,6(4):600-610.
[13]Tang Mingsheng,Mao Xinjun,Guessoum Z,et al. Rumor diffusionin an interests-based dynamic social network[J]. The ScientificWorld Journal,2013,3(8):2-9.
[14]Zhang Xiaoming,Chen Xiaoming,Chen Yan,et al. Event detectionand popularity prediction in microblogging[J]. Neurocomputing,2015,149(2):1469-1480.
[15]Jalali M S,Ashouri A,Herrera-Restrepo O,et al. Information diffu-sion through social networks:the case of an online petition[J]. Ex-pert Systems with Applications,2016,44(2):187-197.
[16]Long Hua,Li Baoan. Overlapping community identification algorithmin directed network[J]. Procedia Computer Science,2017,107(12):527-532.
[2]张树森,梁循,齐金山.社会网络角色识别方法综述[J].计算机学报,2017,40(3):649-673.(Zhang Shusen,Liang Xun,Qi Jin-shan. A review on role identification methods in social networks[J].Chinese Journal of Computers,2017,40(3):649-673.)
[3] Li Feng,Du T C. Maximizing micro-blog influence in online promo-tion[J]. Expert Systems with Applications,2017,70(3):52-66.
[4]吴岘辉,张晖,赵旭剑,等.基于用户行为网络的微博意见领袖挖掘算法[J].计算机应用研究,2015,32(9):2678-2683.(WuXianhui,Zhang Hui,Zhao Xujian,et al. Mining algorithm of mi-croblogging opinion leaders based on user-behavior network[J]. Ap-plication Research of Computers,2015,32(9):2678-2683.)
[5] Deng Xiaolong,Li Yuxiao,Lin Shu. Parallel micro blog crawler con-struction for effective opinion leader approximation[J]. AASRI Pro-cedia,2013,5(3):170-176.
[6]李玉贞,胡勇,熊熙,等.微博意见领袖的评估模型[J].信息安全与通信保密,2013(2):79-81.(Li Yuzhen,Hu Yong,Xiong Xi,etal. Evaluation model of micro-blog opinion leader[J]. InformationSecurity and Communications Privacy,2013(2):79-81.)
[7]赵惠东,刘刚,石川,等.基于转发传播过程的微博转发量预测[J].电子学报,2016,44(12):2989-2996.(Zhao Huidong,LiuGang,Shi Chuan,et al. Retweet number prediction based on retweetpropagation process[J]. Acta Electronica Sinica,2016,44(12):2989-2996.)
[8]张仰森,蒋玉茹,陈若愚,等.微博用户关系网络中意见领袖的分析与挖掘[J].北京信息科技大学学报:自然科学版,2015,30(4):7-14.(Zhang Yangsen,Jiang Yuru,Chen Ruoyu,et al. Analy-sis and mining of opinion leaders in microblog user relationship net-work[J]. Journal of Beijing Information Science&TechnologyUniversity:Natural Science Edition,2015,30(4):7-14.)
[9]冯时,景珊,杨卓,等.基于LDA模型的中文微博话题意见领袖挖掘[J].东北大学学报:自然科学版,2013,34(4):490-494.(FengShi,Jing Shan,Yang Zhuo,et al. Detecting topical opinion leadersbased on LDA model in Chinese microblogs[J]. Journal of Nor-th-eastern University:Natural Science,2013,34(4):490-494.)
[10]丁兆云,周斌,贾焰,等.微博中基于多关系网络的话题层次影响力分析[J].计算机研究与发展,2013,50(10):2155-2175.(DingZhaoyun,Zhou Bin,Jia Yan,et al. Topical influence analysis basedon the multi-relational network in microblogs[J]. Journal of Com-puter Research and Development,2013,50(10):2155-2175.)
[11]董雨辰,刘琰,罗军勇,等.基于支持向量机的炒作微博识别方法[J].计算机工程,2015,41(3):7-14.(Dong Yuchen,Liu Yan,LuoJunyong,et al. Hype Microblog recognition method based on supportvector machine[J]. Computer Engineering,2015,41(3):7-14.)
[12]Wei Jiuchang,Bu Bing,Liang Liang. Estimating the diffusion modelsof crisis information in micro blog[J]. Journal of Informetrics,2012,6(4):600-610.
[13]Tang Mingsheng,Mao Xinjun,Guessoum Z,et al. Rumor diffusionin an interests-based dynamic social network[J]. The ScientificWorld Journal,2013,3(8):2-9.
[14]Zhang Xiaoming,Chen Xiaoming,Chen Yan,et al. Event detectionand popularity prediction in microblogging[J]. Neurocomputing,2015,149(2):1469-1480.
[15]Jalali M S,Ashouri A,Herrera-Restrepo O,et al. Information diffu-sion through social networks:the case of an online petition[J]. Ex-pert Systems with Applications,2016,44(2):187-197.
[16]Long Hua,Li Baoan. Overlapping community identification algorithmin directed network[J]. Procedia Computer Science,2017,107(12):527-532.