Tibetan Weibo User Group Division Based on Semantic Information in the Era of Big Data

Algorithm 2

Improved LDA topic model based on the Weibo text.

Input:News text data: Document1, Weibo text data: Document2

Output: Topic distribution of Weibo short texts: Document_Topics_Matrix

1: training LDA Model by Document1

2: for alld, do

3: combine short texts of microblogs belonging to the same topic to long texts Document3

4: end for

5: for alld, do

6:  predict topics of d by LDA Model

7:  update of LDA_Model

8: end for

9: for alld, do

10: predict topics of d by LDA_Model

11: get Document_Topics_Matrix of d

12: end for

13: returnDocument_Topics_Matrix