基于泊松分布和伽马分布的网络舆情热点发现  

Identifying Online Hot Topics Based on Poisson Distribution and Gamma Distribution

作　　者：罗泰晔[1] 

机构地区：[1]中山大学新华学院,广东广州510520

出　　处：《现代情报》2017年第1期77-80,共4页Journal of Modern Information

摘　　要：本文提出了一种基于泊松分布和伽马分布的网络舆情热点实时识别方法。该方法使用话题的人气和时间间隔特征两方面来识别舆情热点,发现单位时间内(如1小时)参与话题讨论的人数成泊松分布,回帖的时间间隔服从伽马分布。本研究用历史数据证明了该方法具有良好的识别效果。A method was proposed in the paper to identify online hot topics based on Poisson distribution and Gamma distribution, which combined the popularity and time interval characteristics of hot topics. It was found that the number of people participating in a topic discussion per unit time（ e. g. one hour） follows a Poisson distribution, and the time interval between two replies follows a Gamma distribution. Historical data was used to test the effectiveness of the method.

关 键 词：网络热点 网络舆情 伽马分布 泊松分布 热点发现 话题热度 

分 类 号：G203[文化科学—传播学]