%0 Journal Article
%T Study on the Topic Mining and Dynamic Visualization in View of LDA Model | Xie | Modern Applied Science | CCSE
%A Libo Zhu
%A Ping Qin
%A Ting Xie
%J Home | Modern Applied Science | CCSE
%D 2019
%R 10.5539/mas.v13n1p204
%X Text topic mining and visualization are the basis for clustering the topics£¬ distinguishing front topics and hot topics. This paper constructs the LDA topic model based on Python language and researches topic mining£¬ clustering and dynamic visualization£¬taking the metrology of Library and information science in 2017 as an example. In this model£¬parameter and parameter are estimated by Gibbs sampling£¬and the best topic number was determined by coherence scores. The topic mining based on the LDA model can well simulate the semantic information of the large corpus£¬and make the corpus not limited to the key words. The bubble bar graph of the topic-words can present the many-to-many dynamic relationships between the topic and words
%U http://www.ccsenet.org/journal/index.php/mas/article/view/0/38001