Chinese microblog emotion analysis method fused with dominant and recessive characters

The invention discloses a Chinese microblog emotion analysis method fused with dominant and recessive characters. The method comprises the following steps: 1) processing the microblog dominant characters, 1.1) processing emotion icons; 1.2) processing emotion words; 2) processing the microblog recessive characters: based on a frequent item set, creating an initial emotion cluster, wherein each initial emotion cluster text contains the frequent item set, using the Chinese semantic similarity model of the How-Net, and separating each initial emotion cluster according to the maximum semantic membership principle; finally, through defining the inter-cluster semantic similarity model, completing the condensed hierarchical clustering of the microblog emotion cluster, and optimizing to obtain the final emotion cluster, and achieving the microblog emotion analysis. The Chinese microblog emotion analysis method fused with dominant and recessive characters has higher flexibility and better reliability.