Aiming at the lack of searching ability of Biogeography-Based Optimization (BBO) algorithm, an improved migration operation based on local-decision domain was proposed to improve the global optimization ability of the algorithm. The improved migration operation can further utilize the interaction between habitats in consideration of the respective migration rates and evapotranspiration rates of different habitats. The improved algorithm was applied to 12 typical function optimization problems to test the performance, and the effectiveness of the improved algorithm was verified. Compared with BBO, Improved BBO (IBBO) and Differential Evolution/BBO (DE/BBO), the experimental results show that the proposed algorithm can improve the capacity of global searaching optimal solution, convergence speed and computational precision of solution.

In we media platform such as microblog, emergency has such characteristics as suddenness and having multiple bursting points. Thus, it brings difficulty to emergency detection. Thus, this paper proposed a method of bursty events detection based on sentiment filter. Firstly, the topic was mapped as a hierarchical model according to the method. Then, dynamic adjustment of the model characteristics was made in a timing-driven way so as to detect the new topics of the information. Based on it, the method analyzed the user's emotional attitude toward such topics. The topics were divided into positive and negative emotion tendencies according to the user's emotional attitude. Additionally, the topic full of negative emotion tendency was regarded as emergent topic. The experimental results show that the accuracy and recall of the proposed method are all increased about 10% compared with baseline.

It is difficult for the existing methods to get overall sentiment orientation of the comment text. To solve this problem, the method of multi-document sentiment summarization based on Latent Dirichlet Allocation (LDA) model was proposed. In this method, all the subjective sentences were extracted by sentiment analysis and described by LDA model, then a summary was generated based on the weight of sentences which combined the importance of words and the characteristics of sentences. The experimental results show that this method can effectively identify key sentiment sentences, and achieve good results in precision, recall and F-measure.

Chinese comparative sentences are more focused in the field of linguistics. Using machine learning methods to identify comparative sentences, however, has only just started. According to the basic principle of the association rules mining algorithm, a method of comparative sentences based on the associated feature vocabulary was proposed. This method regarded word and part of speech as basic elements, defined the connecting way between the table definition core words and interdependent relationship words, and used the Support Vector Machine (SVM) classifier for the identification of comparative sentences. The experimental results show that this method can effectively identify Chinese comparative sentences, and achieves good results in precision, recall and F-measure.