基于团购商品评论的网络意见领袖识别*

摘要

Network opinion leader's review has an important influence on consumers' purchase decision. Based on the relationship between comments, we construct a directed weighted review reference network. Using the basic idea of PageRank algorithm,an algorithm is presen-ted to identify the network opinion leaders and an empirical study is conducted. The results shows that, compared to the traditional method based on the number of references, this algorithm takes into account the three factors of the number of references, user's influence and de-gree of dependence on other users,thus makes the evaluation more objective. Besides, it reduces the influence of online water army. This paper may helps enterprises greatly in accurately identifying opinion leaders to make better word-of-mouth marketing .%网络意见领袖的评论是消费者购买团购商品时的重要决策依据。基于评论回复关系，构建了有向加权评论引用网络，借鉴PageRank算法的基本思想，提出了网络意见领袖的识别算法，并以北邮人论坛团购版块数据为样本进行了实证研究。分析结果表明，与基于引用次数的传统方法相比，该算法综合考虑了引用次数、引用者自身影响力、用户间引用依赖强度三方面的因素，更加客观地评估用户的意见影响力，并且减小了网络水军对识别结果的影响，进而帮助企业准确识别意见领袖，借助其影响力进行口碑营销。