摘要
传统上用来发掘意见领袖的方法主要有指标权重法和社会网络结构挖掘两大类,但是单纯靠指标权重法发现意见领袖受研究者的主观影响较大,而社会网络结构法中用户间关系较难挖掘且对用户其他属性的衡量有局限性,故而引入了基于粗糙集和AHM算法相结合的综合指标权重算法,充分综合主、客观指标权重挖掘意见领袖,避免了使用单一方法的弊端。通过对新浪微博中热点事件的实例验证,比较了粗糙集-AHM、AHP、社会网络挖掘三种算法的结果,并总结出了本方法计算简单,对用户关系数据依赖程度低、指标评价更加客观的特点。
Traditionally, there are two general types of methods to seek for an opinion leader, which are index weighting method and digging of social network structure. But simply relying on index weighting method to find an opinion leader would be affected by the subjective idea of the opinion leaders, while the method of digging out social network structure is also limited due to the seeming invisible relationship among the users and the unreliable evaluation of the other quality of the users. The article brings up an integrated index weighting algorithm based on rough set and AHM algorithm judging from the goods and weakness of the methods mentioned above. In this way, it is possible to have an integrated index of both subjective and objective standard to judging on the potential opinion leaders in the meantime avoiding the disadvantages of using one single method. The article has some exemplification research on certain hot hits on Weibo. By comparing the output of the three methods, it is concluded that this methods is featured as simple and objective.
出处
《电子科技大学学报（社科版）》
2016年第1期67-71,共5页
Journal of University of Electronic Science and Technology of China(Social Sciences Edition)
基金
浙江省高校人文社科重点研究基地基金（RWSKZD03-201207）
浙江省哲社重点研究基地和浙江省人文社科基金（SIPM3222）：浙江省社科联（20142084）
2014年度国家级大学生创新创业训练计划立项
基于社交网络的“杭州限牌”舆情分析模型构建与实证（201410356019）
2015年新苗人才计划项目（2015R409005）.
