As an innovative way for government affairs disclosure, official microblogs have been widely used in information release, public opinion listening, and public services, which become a model of “Internet + government affairs.” The communication influence of official accounts is mainly related to the account’s attention, activity, and the posted articles. Based on AHP, we design a multi-hierarchy-rank model to filter the factors and determine the most important factors related to the influence of official microblogs. This study explores the communication influence of official microblog from the perspectives of breadth, depth, and intensity; then, a three-dimensional integration of government microblogs influence calculation model for radiation, activity, and interaction is built and a monitoring and analysis system for the communication influence of government microblog is developed; finally, about 2,800 official accounts and more than 1.5 million articles in Zhejiang Province are monitored and analyzed. According to microblog verification, our proposed calculation model not only quantifies the communication influence of official microblogs but also analyzes their dynamics and timeliness. Therefore, it helps government departments to promote the healthy and orderly development of government microblogs.

The development of social media has provided open and convenient platforms for people to express their opinions, which leads to rumors being circulated. Therefore, detecting rumors from massive information becomes particularly essential. Previous methods for rumor detection focused on mining features from content and propagation patterns but neglected the dynamic features with joint content and propagation pattern. In this paper, we propose a novel heterogeneous GCN-based method for dynamic rumor detection (HDGCN), mainly composed of a joint content and propagation module and an ODE-based dynamic module. The joint content and propagation module constructs a content-propagation heterogeneous graph to obtain rumor representations by mining and discovering the interaction between post content and propagation structures in the rumor propagation process. The ODE-based dynamic module leverages a GCN integrated with an ordinary differential system to explore dynamic features of heterogeneous graphs. To evaluate the performance of our proposed HDGCN model, we have conducted extensive experiments on two real-world datasets from Twitter. The results of our proposed model have outperformed the mainstream model.

No abstract

No abstract

No abstract