基于LDA模型的网络党建信息推送策略  

Information Pushing Strategy for Network Party Construction Based on LDA Model

作　　者：杨帆[1] 何敏[1] 施继红[1] 武浩[1] 徐涛 李乐[1] 

机构地区：[1]云南大学信息学院,昆明650091 [2]云南红岭云网络科技有限公司,昆明650091

出　　处：《计算机工程》2016年第9期286-291,共6页Computer Engineering

基　　金：云南省科技创新强省计划基金资助项目"国家农村信息化示范省综合信息服务平台建设关键技术研发与应用"(2014AB016)

摘　　要：针对云南省基层党建综合服务平台推送服务扁平化、效率低等问题,基于潜在狄利克雷分配(LDA)主题模型设计党建信息推送策略。利用LDA模型对用户历史数据进行无监督聚类,根据党员反馈矩阵推测党员偏好,通过待推送信息与党员偏好的相关度实现过滤式党建信息推送。以云岭先锋网手机报真实文本作为实验数据对该策略进行验证,结果表明,相比传统协同过滤和无差别推送方法,该策略更符合实际需求,能取得更稳定的推送效果。Aiming at the shortages of pushing service of Grassroots party building integrated service platform in Yunnan province, such as flatting and inefficiency,this paper proposes a party construction information pushing strategy based on the Latent Dirichlet Allocation（LDA） theme model. It does the unsupervised clustering for user history data by LDA model, deduces the party members preference according to the feedback matrix, then filters and pushes the message to the selected people considering the relevance between the message and the party members＇ preference. At last, as the test data,the real mobile news text on the website of Yunling Pioneer is input in the experimental tests and the results show that this strategy is more stable. It can meet the needs of the real application compared with the traditional collaborative filtering algorithm and undifferentiated pushing method.

关 键 词：网络党建 信息推送 主题模型 党员偏好推断 潜在狄利克雷分配模型 

分 类 号：TP301[自动化与计算机技术—计算机系统结构]