It is a great challenge to discover communities in the fast growing large-scale interactive social information networks such as Weibo and social networks. Although Label Propagation Algorithm (LPA) has great advantage in time complexity, but its inherent multiple random strategies make the algorithm unstable. In order to solve the problem, a semi-synchronous label propagation algorithm named Influence-driven Semi-synchronous Label Propagation Algorithm (ISLPA) was proposed. The propagation oscillation was avoided effectively and the synchronous update between neighbor nodes was realized by abandoning the original random strategy and integrating node influence into label initialization, neighbor node selection and updated order determination. The experimental results from the real-world and artificial networks indicate that, in terms of validity and stability of generated communities from the networks, the proposed ISLPA outperforms the currently typical LPAs used in community detection.

For the problem of existing models' disability to analyze topic-sentiment evolution of microblogs, a Dynamic Topic Sentiment Combining Model (DTSCM) was proposed based on Topic Sentiment Combining Model (TSCM) and the emotional cycle theory. DTSCM could track the topic sentiment evolution trend and obtain the graph of topic sentiment evolution so as to analyze the evolution of topic and sentiment by capturing the topic and sentiment of microblogs in different time. The experimental results in real microblog corpus showed that, in contrast with state-of-the-art models Joint Sentiment/Topic (JST), Sentiment-Latent Dirichlet Allocation (S-LDA) and Dependency Phrases-Latent Dirichlet Allocation (DPLDA), the sentiment classification accuracy of DTSCM increased by 3.01%, 4.33% and 8.75% respectively,and DTSCM could obtain topic-sentiment evolution of microblogs. The proposed approach can not only achieve higher sentiment classification accuracy but also analyze topic-sentiment evolution of microblog, and it is helpful for public opinion analysis.