一种分布式LDA主题模型方法

A distributed LDA topic modeling

基于Spark分布式计算框架,采用Gibbs抽样方法研究分布式LDA主题模型挖掘方法。在Spark平台进行大规模数据集处理实验。

Based on spark distributed computing framework,we apply Gibbs sampling to study the distributed latent topic information（LDA）mining method.In Spark platform,experiment based on large data sets is carried.